archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 621-640 of 3623 records
Limitations of Reward Modeling is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with huma...
Limitations of Human Feedback is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.0 > AI system safety, failures, & limitations. It is...
Reward Tampering is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with human goals or val...
Goal Misgeneralization is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with human goals...
Reward Hacking is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with human goals or value...
Causes of Misalignment is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with human goals...
Adult content is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 3 - Other.
Information on harmful, immoral, or illegal activity is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most rel...
Misinformation is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 3 - Other.
Alignment risks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with human goals or valu...
AI Development is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most relevant durin...
Long-horizon Planning is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most relevan...
Political Strategy is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most relevant d...
Deception is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most relevant during 3 -...
Persuasion and manipulation is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most r...
Extreme Risks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.0 > AI system safety, failures, & limitations. It is most relevant d...
Robustness is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant during 3 - Ot...
Machine ethics is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant during 3...
Bias is an AI risk in 1. Discrimination & Toxicity focused on 1.1 > Unfair discrimination and misrepresentation. It is most relevant during 3 - Other.
Toxicity generation is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant during 3 - Other.