Skip to Content
logologo
AI Incident Database
Open TwitterOpen RSS FeedOpen FacebookOpen LinkedInOpen GitHub
Open Menu
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる
発見する
投稿する
  • ようこそAIIDへ
  • インシデントを発見
  • 空間ビュー
  • テーブル表示
  • リスト表示
  • 組織
  • 分類法
  • インシデントレポートを投稿
  • 投稿ランキング
  • ブログ
  • AIニュースダイジェスト
  • リスクチェックリスト
  • おまかせ表示
  • サインアップ
閉じる
組織

Anthropic

開発者と提供者の両方の立場で関わったインシデント

インシデント 7344 Report
Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

2024-06-18

An audit by NewsGuard revealed that leading chatbots, including ChatGPT-4, You.com’s Smart Assistant, and others, repeated Russian disinformation narratives in one-third of their responses. These narratives originated from a network of fake news sites created by John Mark Dougan (Incident 701). The audit tested 570 prompts across 10 AI chatbots, showing that AI remains a tool for spreading disinformation despite efforts to prevent misuse.

もっと

インシデント 10442 Report
Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

2025-04-15

Researchers reportedly traced the appearance of the nonsensical phrase "vegetative electron microscopy" in scientific papers to contamination in AI training data. Testing indicated that large language models such as GPT-3, GPT-4, and Claude 3.5 may reproduce the term. The error allegedly originated from a digitization mistake that merged unrelated words during scanning, and a later translation error between Farsi and English.

もっと

インシデント 8591 Report
AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

2024-10-30

An analysis reportedly found that multiple AI models provided inaccurate responses to election-related questions, with 52% of Spanish-language answers and 43% of English-language answers containing misinformation or omissions. Errors included misidentifying voting processes and providing information about foreign elections.

もっと

インシデント 10261 Report
Multiple LLMs Allegedly Endorsed Suicide as a Viable Option During Non-Adversarial Mental Health Venting Session

2025-04-12

Substack user @interruptingtea reports that during a non-adversarial venting session involving suicidal ideation, multiple large language models (Claude, GPT, and DeepSeek) responded in ways that allegedly normalized or endorsed suicide as a viable option. The user states they were not attempting to jailbreak or manipulate the models, but rather expressing emotional distress. DeepSeek reportedly reversed its safety stance mid-conversation.

もっと

Incidents involved as Developer

インシデント 96826 Report
'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

2022-02-24

A 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.

もっと

インシデント 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.

もっと

インシデント 9751 Report
At Least 10,000 AI Chatbots, Including Jailbroken Models, Allegedly Promote Eating Disorders, Self-Harm, and Sexualized Minors

2025-03-05

At least 10,000 AI chatbots have allegedly been created to promote harmful behaviors, including eating disorders, self-harm, and the sexualization of minors. These chatbots, some jailbroken or custom-built, leverage APIs from OpenAI, Anthropic, and Google and are hosted on platforms like Character.AI, Spicy Chat, Chub AI, CrushOn.AI, and JanitorAI.

もっと

関連団体
同じインシデントに関連するその他のエンティティ。たとえば、インシデントの開発者がこのエンティティで、デプロイヤーが別のエンティティである場合、それらは関連エンティティとしてマークされます。
 

Entity

You.com

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

xAI

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Perplexity

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

OpenAI

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 975
    1 レポート

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

もっと
Entity

Mistral

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Microsoft

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Meta

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

John Mark Dougan

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Inflection

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Google

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

Incidents involved as Developer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 975
    1 レポート

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

もっと
Entity

Western democracies

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Volodymyr Zelenskyy

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Ukraine

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Secret Service

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Researchers

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

Incidents involved as Deployer
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Media consumers

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

General public

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Electoral integrity

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

AI companies facing reputational damage

影響を受けたインシデント
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

You.com Smart Assistant

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

xAI Grok

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Perplexity Answer Engine

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Mistral le Chat

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Meta AI

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Inflection AI Pi

Incidents implicated systems
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Gemini

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Copilot

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

ChatGPT

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Anthropic Claude

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

167 fake local news websites operated by John Mark Dougan

Incidents implicated systems
  • インシデント 734
    4 レポート

    Leading AI Models Reportedly Found to Mimic Russian Disinformation in 33% of Cases and to Cite Fake Moscow News Sites

もっと
Entity

Spanish speakers

影響を受けたインシデント
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Spanish-speaking American voters

影響を受けたインシデント
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

U.S. electorate

影響を受けたインシデント
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Democracy

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Claude 3

Incidents implicated systems
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Gemini 1.5 Pro

Incidents implicated systems
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

ChatGPT 4

Incidents implicated systems
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Llama 3

Incidents implicated systems
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

Mixtral 8x7B

Incidents implicated systems
  • インシデント 859
    1 レポート

    AI Models Reportedly Found to Provide Misinformation on Election Processes in Spanish

もっと
Entity

TigerWeb

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Storm-1516

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Russian state media

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Pravda disinformation network

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Portal Kombat

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Government of Russia

Incidents involved as Deployer
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Truth

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Policymakers

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Journalists

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Journalism

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Governments

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Government of Ukraine

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

General public of Ukraine

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Chatbot users

影響を受けたインシデント
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Inflection Pi

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

ChatGPT 4o

Incidents implicated systems
  • インシデント 968
    26 レポート

    'Pravda' Network, Successor to 'Portal Kombat,' Allegedly Seeding AI Models with Kremlin Disinformation

もっと
Entity

Character.AI

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

Spicy Chat

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

Chub AI

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

CrushOn.AI

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

JanitorAI

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

Unidentified online communities using chatbots

Incidents involved as Deployer
  • インシデント 975
    1 レポート

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

もっと
Entity

Vulnerable chatbot users

影響を受けたインシデント
  • インシデント 975
    1 レポート

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

もっと
Entity

Teenagers using chatbots

影響を受けたインシデント
  • インシデント 975
    1 レポート

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

もっと
Entity

Minors using chatbots

影響を受けたインシデント
  • インシデント 975
    1 レポート

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

もっと
Entity

Individuals with eating disorders

影響を受けたインシデント
  • インシデント 975
    1 レポート

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

もっと
Entity

Individuals struggling with self-harm

影響を受けたインシデント
  • インシデント 975
    1 レポート

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

もっと
Entity

Claude

Incidents implicated systems
  • インシデント 1054
    5 レポート

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

  • インシデント 1026
    1 レポート

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

もっと
Entity

DeepSeek AI

開発者と提供者の両方の立場で関わったインシデント
  • インシデント 1026
    1 レポート

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

もっと
Entity

Substack @interruptingtea

影響を受けたインシデント
  • インシデント 1026
    1 レポート

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

もっと
Entity

Emotionally vulnerable individuals

影響を受けたインシデント
  • インシデント 1026
    1 レポート

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

もっと
Entity

DeepSeek

Incidents implicated systems
  • インシデント 1026
    1 レポート

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

もっと
Entity

Scientific authors

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

Incidents involved as Deployer
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Scientific publishers

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Peer reviewers

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Scholars

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Readers of scientific publications

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Scientific record

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Academic integrity

影響を受けたインシデント
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

GPT-3

Incidents implicated systems
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

GPT-4

Incidents implicated systems
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Claude 3.5

Incidents implicated systems
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Common Crawl

Incidents implicated systems
  • インシデント 1044
    2 レポート

    Reported Emergence of 'Vegetative Electron Microscopy' in Scientific Papers Traced to Purported AI Training Data Contamination

もっと
Entity

Unknown malicious actors

Incidents involved as Deployer
  • インシデント 1054
    5 レポート

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

もっと
Entity

Unknown cybercriminals

Incidents involved as Deployer
  • インシデント 1054
    5 レポート

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

もっと
Entity

Influence-as-a-service operators

Incidents involved as Deployer
  • インシデント 1054
    5 レポート

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

もっと
Entity

social media users

影響を受けたインシデント
  • インシデント 1054
    5 レポート

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

もっと
Entity

People targeted by malware

影響を受けたインシデント
  • インシデント 1054
    5 レポート

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

もっと
Entity

Job seekers in Eastern Europe

影響を受けたインシデント
  • インシデント 1054
    5 レポート

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

もっと
Entity

IoT security camera owners

影響を受けたインシデント
  • インシデント 1054
    5 レポート

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

もっと
Entity

LLM-enhanced malware toolkits

Incidents implicated systems
  • インシデント 1054
    5 レポート

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

もっと
Entity

Claude AI models

Incidents implicated systems
  • インシデント 1054
    5 レポート

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

もっと
Entity

AI-generated social media bots

Incidents implicated systems
  • インシデント 1054
    5 レポート

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

もっと

リサーチ

  • “AIインシデント”の定義
  • “AIインシデントレスポンス”の定義
  • データベースのロードマップ
  • 関連研究
  • 全データベースのダウンロード

プロジェクトとコミュニティ

  • AIIDについて
  • コンタクトとフォロー
  • アプリと要約
  • エディタのためのガイド

インシデント

  • 全インシデントの一覧
  • フラグの立ったインシデント
  • 登録待ち一覧
  • クラスごとの表示
  • 分類法

2024 - AI Incident Database

  • 利用規約
  • プライバシーポリシー
  • Open twitterOpen githubOpen rssOpen facebookOpen linkedin
  • 1420c8e