category
AI Risks
Common risks that can happen when AI systems are built, deployed, or used.
Showing 801-820 of 1686 records
Impacts of AI (Societal Impacts) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
Impacts of AI (Financial Impacts) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
AI Systems interacting with brittle environments is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustn...
Damage to critical infrastructure is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most...
Impacts of AI (Physical) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
Competitive pressures in GPAI product release is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant...
Democratizing access to dual-use technologies is an AI risk in 4. Malicious Actors & Misuse focused on 4.0 > Malicious use. It is most relevant during 2 - Po...
Impacts of AI (General) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
Deployment (Model Release) is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.
Agency (Persuasive capabilities) is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is m...
Situational awareness in AI systems is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It i...
Agency (Situational Awareness) is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is mos...
Deceptive behavior leading to unauthorized actions is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous cap...
Deceptive behavior because of an incorrect world model is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous...
Deceptive behavior for game-theoretical reasons is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabi...
Deceptive behavior 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 v...
Agency (Deception) 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 v...
Goal misgeneralization is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant d...
Specification gaming generalizing to reward tampering is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goal...
Reward or measurement tampering is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with hum...