archive

All Records

AI security records indexed from public vulnerability, risk, and attack datasets.

Showing 121-140 of 3623 records

Rapid development outpacing regulation

Rapid development outpacing regulation is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. It is most relevant during 3...

Personal decision automation capabilities

Personal decision automation capabilities is an AI risk in 5. Human-Computer Interaction focused on 5.2 > Loss of human agency and autonomy. It is most relev...

Pattern recognition capability

Pattern recognition capability is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.6 > Multi-agent risks. It is most relevant during 2...

Opaque AI networks

Opaque AI networks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.4 > Lack of transparency or interpretability. It is most releva...

Model design enabling power-seeking

Model design enabling power-seeking is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in conflict with...

Limited human oversight in decisions

Limited human oversight in decisions is an AI risk in 5. Human-Computer Interaction focused on 5.2 > Loss of human agency and autonomy. It is most relevant d...

Limitations in model generative accuracy

Limitations in model generative accuracy is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale...

Limitations in adversarial robustness

Limitations in adversarial robustness is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most rele...

Incomplete or biased training data

Incomplete or biased training data is an AI risk in 1. Discrimination & Toxicity focused on 1.1 > Unfair discrimination and misrepresentation. It is most rel...

Human choice of overreliance in critical sectors

Human choice of overreliance in critical sectors is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most rele...

High-speed AI operations

High-speed AI operations is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant during 2 - Post-deplo...

Geopolitical competition for superiority

Geopolitical competition for superiority is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant durin...

Exploitation in AI development

Exploitation in AI development is an AI risk in 6. Socioeconomic and Environmental focused on 6.2 > Increased inequality and decline in employment quality. I...

Evolutionary dynamics

Evolutionary dynamics 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 o...

Energy-intensive processes

Energy-intensive processes is an AI risk in 6. Socioeconomic and Environmental focused on 6.6 > Environmental harm. It is most relevant during 1 - Pre-deploy...

Dual-use nature

Dual-use nature is an AI risk in 4. Malicious Actors & Misuse focused on 4.0 > Malicious use. It is most relevant during 2 - Post-deployment.

Detection challenges in content

Detection challenges in content is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of consensus reality. It is m...

Dependency on providers

Dependency on providers is an AI risk in 6. Socioeconomic and Environmental focused on 6.1 > Power centralization and unfair distribution of benefits. It is...

Deceptive alignment

Deceptive alignment 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...

Dangerous development races

Dangerous development races is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant during 1 - Pre-dep...