Anthropic
Incidents impliqués en tant que développeur et déployeur
Incident 162715 Rapports
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.
PlusIncident 162815 Rapports
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.
PlusIncident 162915 Rapports
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.
PlusIncident 165711 Rapports
Anthropic Allegedly Copied Copyrighted Song Lyrics Without Permission to Train Claude
2023-09-27
Music publishers alleged that Anthropic copied copyrighted song lyrics without permission to train Claude and that Claude reproduced protected lyrics in its outputs. Anthropic denied infringement and has argued that its training use is fair use. Publishers alleged that the conduct deprived rightsholders and songwriters of licensing control and revenue and undermined markets for licensed lyrics.
PlusAffecté par des incidents
Incident 13954 Rapports
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
2026-02-23
Anthropic said it identified large-scale campaigns that used fraudulent accounts and proxy services to generate high volumes of Claude interactions to extract model capabilities for competitor training ("distillation"). Anthropic attributed the activity to DeepSeek, Moonshot, and MiniMax and said it involved millions of exchanges across thousands of accounts, violating its terms and access restrictions. Anthropic described detection measures, account controls, and indicator-sharing in response.
PlusIncident 10743 Rapports
Citation Errors in Concord Music v. Anthropic Attributed to Claude AI Use by Defense Counsel
2025-05-15
In a legal filing in Universal Music Group et al. v. Anthropic, lawyers for Anthropic acknowledged that expert witness testimony submitted in the case contained erroneous citations generated by the company's Claude AI system. The filing stated that the inaccuracies, which included incorrect article titles and author names, were not caught during manual review. Anthropic characterized the issue as an honest mistake and apologized in court.
PlusIncident 16133 Rapports
Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation
2026-04-07
During an Anthropic evaluation, an earlier version of Claude Mythos Preview was instructed to circumvent the network restrictions of a secured sandbox environment and contact a researcher. After obtaining broader Internet access and sending the requested message, it later exposed information about how it breached the sandbox by posting it on several publicly reachable websites. Anthropic said the model did not access its weights or internal systems.
PlusIncidents involved as Developer
Incident 126334 Rapports
Chinese State-Linked Operator (GTG-1002) Reportedly Uses Claude Code for Autonomous Cyber Espionage
2025-11-13
Anthropic reportedly identified a cyber espionage campaign in which a purported Chinese state-linked group, designated GTG-1002 by Anthropic, allegedly jailbroke Claude Code and used it to automate 80–90% of multi-stage intrusions. The AI reportedly independently performed reconnaissance, vulnerability discovery, exploitation, credential harvesting, and data extraction across roughly 30 targets before the activity was detected and blocked.
PlusIncident 96827 Rapports
'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation
2022-02-24
A purported Moscow-based disinformation network, Pravda, allegedly infiltrated AI models by flooding the internet with pro-Kremlin falsehoods. A NewsGuard audit found that 10 major AI chatbots repeated these narratives 33% of the time, citing Pravda sources as legitimate. The tactic, called "LLM grooming," manipulates AI training data to embed Russian propaganda. Pravda is part of Portal Kombat, a larger Russian disinformation network identified by VIGINUM in February 2024, but in operation since February 2022.
PlusIncident 10545 Rapports
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.
PlusIncident 13954 Rapports
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
2026-02-23
Anthropic said it identified large-scale campaigns that used fraudulent accounts and proxy services to generate high volumes of Claude interactions to extract model capabilities for competitor training ("distillation"). Anthropic attributed the activity to DeepSeek, Moonshot, and MiniMax and said it involved millions of exchanges across thousands of accounts, violating its terms and access restrictions. Anthropic described detection measures, account controls, and indicator-sharing in response.
PlusEntités liées
Autres entités liées au même incident. Par exemple, si le développeur d'un incident est cette entité mais que le responsable de la mise en œuvre est une autre entité, ils sont marqués comme entités liées.
Entités liées
You.com
Incidents impliqués en tant que développeur et déployeur
Incidents involved as Developer
xAI
Incidents impliqués en tant que développeur et déployeur
- Incident 11865 Report
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
Incidents involved as Developer
Perplexity
Incidents impliqués en tant que développeur et déployeur
Incidents involved as Developer
OpenAI
Incidents impliqués en tant que développeur et déployeur
- Incident 11865 Report
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
Incidents involved as Developer
Mistral
Incidents impliqués en tant que développeur et déployeur
- Incident 11865 Report
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
Incidents involved as Developer
Incidents implicated systems
Microsoft
Incidents impliqués en tant que développeur et déployeur
- Incident 11865 Report
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
Incidents involved as Developer
Meta
Incidents impliqués en tant que développeur et déployeur
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
- Incident 8591 Report
AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish
Incidents involved as Developer
Inflection
Incidents impliqués en tant que développeur et déployeur
Incidents involved as Developer
Incidents impliqués en tant que développeur et déployeur
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
- Incident 8591 Report
AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish
Incidents involved as Developer
- Incident 96827 Report
'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation
- Incident 12102 Report
Malicious Nx npm Packages Reportedly Weaponize AI Coding Agents for Data Exfiltration
Incidents implicated systems
Researchers
Affecté par des incidents
- Incident 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites
- Incident 10442 Report
Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination
Incidents involved as Deployer
DeepSeek
Incidents involved as Deployer
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Incidents implicated systems
Malicious actors compromising Nx’s CI/CD pipeline and publishing tainted npm packages
Incidents involved as Deployer
State-linked operator using autonomous AI-enabled intrusion workflows
Incidents involved as Deployer
Moonshot AI
Incidents involved as Deployer
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
MiniMax
Incidents involved as Deployer
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Proxy reseller services
Incidents involved as Deployer
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Claude users
Affecté par des incidents
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Anthropic customers
Affecté par des incidents
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Claude API
Incidents implicated systems
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Distillation
Incidents implicated systems
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Model extraction
Incidents implicated systems
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Account farming
Incidents implicated systems
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
Proxy access infrastructure
Incidents implicated systems
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale
- Incident 13954 Report
Anthropic Said DeepSeek, Moonshot, and MiniMax Used Fraudulent Accounts and Proxies to Illicitly Distill Claude Capabilities at Scale