Skip to Content
logologo
AI Incident Database
Donate
Discover
Submit
  • Welcome to the AIID
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Spatial View
  • Blog
  • AI News Digest
  • Random Incident
  • Sign Up
Discover
Submit
  • Welcome to the AIID
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Spatial View
  • Blog
  • AI News Digest
  • Random Incident
  • Sign Up
Entities

Claude

Incidents implicated systems

Incident 162713 Report
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation conducted with Irregular, Claude Opus 4.7 reportedly reached a real company whose domain matched a fictional target, extracted application and infrastructure credentials, and accessed a database containing several hundred rows of production data. Across four runs, the model continued attacking after recognizing that the target was likely real.

More

Incident 162813 Report
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation with Irregular, Claude Mythos 5 reportedly created and published a malicious Python package to PyPI while pursuing a fictional target. The package was reportedly available for about an hour and ran on 15 real systems. On a security company's scanner, it reportedly exfiltrated credentials that Claude then used to access additional company infrastructure.

More

Incident 162913 Report
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation with Irregular, an internal research Claude model reportedly scanned roughly 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials from an exposed debug page and SQL injection, then stopped after recognizing that the host was real.

More

Incident 10545 Report
Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

2025-04-23

In April 2025, Anthropic published a report detailing several misuse cases involving its Claude LLM, all detected in March. These included an "influence-as-a-service" operation that orchestrated over 100 social media bots; an effort to scrape and test leaked credentials for security camera access; a recruitment fraud campaign targeting Eastern Europe; and a novice actor developing sophisticated malware. Anthropic banned the accounts involved but could not confirm downstream deployment.

More

Related Entities
Other entities that are related to the same incident. For example, if the developer of an incident is this entity but the deployer is another entity, they are marked as related entities.
 

Entity

Character.ai

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Spicy Chat

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Chub AI

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

CrushOn.AI

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

JanitorAI

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Unidentified online communities using chatbots

Incidents involved as Deployer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

OpenAI

Incidents involved as both Developer and Deployer
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1026
    1 Report

    Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

Incidents involved as Developer
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Anthropic

Incidents involved as both Developer and Deployer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

Incidents Harmed By
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

Incidents involved as Developer
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Google

Incidents involved as Developer
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Vulnerable chatbot users

Incidents Harmed By
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Teenagers using chatbots

Incidents Harmed By
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Minors using chatbots

Incidents Harmed By
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Individuals with eating disorders

Incidents Harmed By
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

Individuals struggling with self-harm

Incidents Harmed By
  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

ChatGPT

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Gemini

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

  • Incident 975
    1 Report

    At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

More
Entity

DeepSeek AI

Incidents involved as both Developer and Deployer
  • Incident 1026
    1 Report

    Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

More
Entity

Substack @interruptingtea

Incidents Harmed By
  • Incident 1026
    1 Report

    Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

More
Entity

General public

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Emotionally vulnerable individuals

Incidents Harmed By
  • Incident 1026
    1 Report

    Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

More
Entity

DeepSeek

Incidents involved as Deployer
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

  • Incident 1026
    1 Report

    Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

More
Entity

Malicious actors

Incidents involved as Deployer
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Influence-as-a-service operators

Incidents involved as Deployer
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Cybercriminals

Incidents involved as Deployer
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Social media users

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

People targeted by malware

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Job seekers in Eastern Europe

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

IoT security camera owners

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Epistemic integrity

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

National security and intelligence stakeholders

Incidents Harmed By
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

LLM-enhanced malware toolkits

Incidents implicated systems
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Claude AI models

Incidents implicated systems
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

AI-generated social media bots

Incidents implicated systems
  • Incident 1054
    5 Reports

    Anthropic Report Details Claude Misuse for Influence Operations, Credential Stuffing, Recruitment Fraud, and Malware Development

More
Entity

Judicial integrity

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Ivana Dukanovic

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Brittany N. Lovejoy

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Joseph R. Wetzel

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Andrew M. Gass

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Allison L. Stillman

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Sarang V. Damle

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Sara E. Sampoli

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Rachel S. Horn

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

Latham & Watkins LLP

Incidents Harmed By
  • Incident 1074
    3 Reports

    Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel

More
Entity

xAI

Incidents involved as both Developer and Deployer
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Mistral

Incidents involved as both Developer and Deployer
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Microsoft

Incidents involved as both Developer and Deployer
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Alibaba

Incidents involved as both Developer and Deployer
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Users of Qwen

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Users of Mistral

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Users of Grok

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Users of Copilot

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Users of Claude

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Privacy

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

ChatGPT users

Incidents Harmed By
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Wayback Machine

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Qwen

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Internet Archive

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

More
Entity

Grok

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Copilot

Incidents implicated systems
  • Incident 1186
    5 Reports

    Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Ransomware-as-a-service actors

Incidents involved as Deployer
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

North Korean IT operatives

Incidents involved as Deployer
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Government of North Korea

Incidents involved as Deployer
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Religious institutions

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Healthcare organizations

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Government agencies

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

Incidents involved as Deployer
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Fortune 500 technology companies

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Emergency services

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Consumers targeted by ransomware

Incidents Harmed By
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

LLM-enhanced ransomware toolkits

Incidents implicated systems
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

Claude Code

Incidents implicated systems
  • Incident 1201
    3 Reports

    Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales

More
Entity

AI agent systems

Incidents implicated systems
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Urban Cyber Security

Incidents involved as both Developer and Deployer
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

BiScience

Incidents involved as Developer
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Urban VPN Proxy users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Perplexity users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Meta AI users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Grok users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Gemini users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

DeepSeek users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Copilot users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Claude users

Incidents Harmed By
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Chatbot users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Browser extension users

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Chatbot developers

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

Incidents involved as Developer
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

Large language model developers

Incidents Harmed By
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

Incidents involved as Developer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Urban VPN Proxy

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Perplexity

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Meta AI

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

More
Entity

Large language models

Incidents implicated systems
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Chatbots

Incidents implicated systems
  • Incident 1356
    3 Reports

    Urban VPN Proxy Browser Extension Reportedly Harvested and Sold Private AI Chatbot Conversations via Silent Update

  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Moonshot AI

Incidents involved as Deployer
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

MiniMax

Incidents involved as Deployer
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Proxy reseller services

Incidents involved as Deployer
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Anthropic customers

Incidents Harmed By
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Claude API

Incidents implicated systems
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Distillation

Incidents implicated systems
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Model extraction

Incidents implicated systems
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Account farming

Incidents implicated systems
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Proxy access infrastructure

Incidents implicated systems
  • Incident 1395
    4 Reports

    Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale

More
Entity

Hackers

Incidents involved as Deployer
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Mexican taxpayers

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Mexican voters

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Mexican government employees

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

State government of Tamaulipas

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

State government of Michoacán

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

State government of Jalisco

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Monterrey Water and Drainage Services

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Servicio de Administración Tributaria (SAT)

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Instituto Nacional Electoral (INE)

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

Dirección General del Registro Civil de la Ciudad de México (DGRC)

Incidents Harmed By
  • Incident 1430
    2 Reports

    Anthropic's Claude Was Reportedly Jailbroken To Allegedly Help Steal Sensitive Mexican Government Data

More
Entity

United States military

Incidents involved as Deployer
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

United States Department of Defense

Incidents involved as Deployer
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

United States Central Command

Incidents involved as Deployer
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Palantir

Incidents involved as Developer
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Teachers

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Students

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Shajareh Tayyebeh Primary School community

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Shajareh Tayyebeh Primary School

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Minors

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Iranian teachers

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Iranian schoolchildren

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Iranian civilians

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

General public of Iran

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Educators

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Educational communities

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Minab school-strike victims and families

Incidents Harmed By
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Maven Smart System

Incidents implicated systems
  • Incident 1492
    2 Reports

    Purportedly AI-Enabled Targeting System Was Reportedly Implicated in Deadly U.S. Strike on Iranian Primary School

More
Entity

Writers

Incidents involved as Deployer
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Steven Rosenbaum

Incidents involved as Deployer
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Authors

Incidents involved as Deployer
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Readers

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

People misquoted by AI-assisted books

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Meredith Broussard

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Lisa Feldman Barrett

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Lee McIntyre

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Kara Swisher

Incidents Harmed By
  • Incident 1504
    1 Report

    Nonfiction Book 'The Future of Truth' Reportedly Included AI-Generated and Misattributed Quotations

More
Entity

Anthropic users

Incidents Harmed By
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Search engines

Incidents implicated systems
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Public sharing features

Incidents implicated systems
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Google Search

Incidents implicated systems
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Claude public sharing links

Incidents implicated systems
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Claude Artifacts

Incidents implicated systems
  • Incident 1621
    2 Reports

    Publicly Shared Claude Artifacts Reportedly Became Discoverable Through Google Search

More
Entity

Irregular

Incidents involved as Deployer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

AI evaluation organizations

Incidents involved as Deployer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

AI agent system deployers

Incidents involved as Deployer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

AI agent system developers

Incidents involved as Developer
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Unidentified companies compromised during Anthropic cybersecurity evaluations disclosed July 2026

Incidents Harmed By
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Companies

Incidents Harmed By
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Claude Opus 4.7

Incidents implicated systems
  • Incident 1627
    13 Reports

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

More
Entity

Python Package Index (PyPI) ecosystem

Incidents implicated systems
  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

More
Entity

Cybersecurity AI systems

Incidents implicated systems
  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

  • Incident 1629
    13 Reports

    Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

More
Entity

Claude Mythos 5

Incidents implicated systems
  • Incident 1628
    13 Reports

    Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Internal Anthropic research test models

Incidents implicated systems
  • Incident 1629
    13 Reports

    Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

More
Entity

AI Security Institute (United Kingdom)

Incidents involved as Deployer
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Software developers

Incidents Harmed By
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Open-source maintainers

Incidents Harmed By
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

GitHub users

Incidents Harmed By
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Supply chains

Incidents implicated systems
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Software ecosystems

Incidents implicated systems
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

GPT-5.6 Sol

Incidents implicated systems
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

GitHub repositories

Incidents implicated systems
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

GitHub

Incidents implicated systems
  • Incident 1633
    2 Reports

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

More
Entity

Office of Rep. Anna Paulina Luna

Incidents involved as Deployer
  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

Congressional staffers

Incidents involved as Deployer
  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

General public of the United States

Incidents Harmed By
  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

Congressional public records

Incidents Harmed By
  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

Congressional publishing workflows

Incidents implicated systems
  • Incident 1641
    2 Reports

    Rep. Anna Paulina Luna's Office Reportedly Published Claude Transcript Residue on Accident in House Amendment Summary

More
Entity

Andrew Bird

Incidents involved as Deployer
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Peter Steinberger

Incidents involved as Developer
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Gym member removed from waitlist by Andrew Bird's AI agent

Incidents Harmed By
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Gym members

Incidents Harmed By
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Users of online booking systems

Incidents Harmed By
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

AI agent system users

Incidents Harmed By
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

OpenClaw users

Incidents Harmed By
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

OpenClaw

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Claude Opus 4.6

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

AI agent system

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Online booking systems

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

Gym booking software

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More
Entity

GraphQL APIs

Incidents implicated systems
  • Incident 1642
    2 Reports

    AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

More

Research

  • Defining an “AI Incident”
  • Defining an “AI Incident Response”
  • Database Roadmap
  • Related Work
  • Download Complete Database

Project and Community

  • About
  • Contact and Follow
  • Apps and Summaries
  • Editor’s Guide

Incidents

  • All Incidents in List Form
  • Flagged Incidents
  • Submission Queue
  • Classifications View
  • Taxonomies

2026 - AI Incident Database

  • Terms of use
  • Privacy Policy
  • dd3f754