category
AI Risks
Common risks that can happen when AI systems are built, deployed, or used.
Showing 1541-1560 of 1769 records
Amplification of cyberattacks is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is mo...
Attacks on GPAIs/GPAI Failure Modes is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
Direct Harm Domains (content safety harms) is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic content. It is most relevant duri...
Physical Hazards is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.
AI-Powered Spear-Phishing at Scale is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is...
Surveillance and Censorship is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most r...
Privacy and Data Protection is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive informa...
Harming users’ data privacy is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive informa...
Poor model accuracy is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant duri...
Fine-tuning related (Excessive or overly restrictive safety-tuning) is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of ca...
Fine-tuning related (Unexpected competence in fine-tuned versions of the upstream model) is an AI risk in 7. AI System Safety, Failures, & Limitations focuse...
Reinforcement learning AI (Training performance related) is an AI risk focused on X.1 > Excluded. It is most relevant during 1 - Pre-deployment.
Supervised/unsupervised AI (AI data quality related - biased training data) is an AI risk focused on X.1 > Excluded. It is most relevant during 1 - Pre-deplo...
Dimension - Technical Attributes (AI inadequacy - technical failure) is an AI risk focused on X.1 > Excluded. It is most relevant during 1 - Pre-deployment.
Lack of capability for task is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relev...
Nascent capabilities (agency and autonomy) is an AI risk.
4.0 > Malicious use groups 24 AI risk records under 4. Malicious Actors & Misuse.
Risk area 5: Human-Computer Interaction Harms is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most relevan...
Generation of personalized content for harassment, extortion, or intimidation is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, an...
Interconnectivity with malicious external tools is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is...