archive

All Records

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

Showing 701-720 of 3623 records

Proxy Gaming

Proxy Gaming 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 values...

Rogue AIs (Internal)

Rogue AIs (Internal) 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...

Organizational Factors can Reduce the Chances of Catastrophe

Organizational Factors can Reduce the Chances of Catastrophe is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.

Accidents Are Hard to Avoid

Accidents Are Hard to Avoid is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. It is most relevant during 3 - Other.

Organizational Risks (Accidental)

Organizational Risks (Accidental) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.

Corporate AI Race

Corporate AI Race is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant during 3 - Other.

Military AI Arms Race

Military AI Arms Race is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant during 3 - Other.

AI Race (Environmental/Structural)

AI Race (Environmental/Structural) is an AI risk in 6. Socioeconomic and Environmental focused on 6.4 > Competitive dynamics. It is most relevant during 3 -...

Concentration of Power

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

Persuasive AIs

Persuasive AIs is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most relevant durin...

Unleashing AI Agents

Unleashing AI Agents is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most releva...

Bioterrorism

Bioterrorism is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most relevant durin...

Malicious Use (Intentional)

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

Power-seeking behavior

Power-seeking 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...

Emergent functionality

Emergent functionality is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most releva...

Value lock-in

Value lock-in is an AI risk in 6. Socioeconomic and Environmental focused on 6.1 > Power centralization and unfair distribution of benefits. It is most relev...

Proxy misspecification

Proxy misspecification 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...

Eroded epistemics

Eroded epistemics is an AI risk in 3. Misinformation focused on 3.2 > Pollution of information ecosystem and loss of consensus reality. It is most relevant d...

Enfeeblement

Enfeeblement is an AI risk in 5. Human-Computer Interaction focused on 5.2 > Loss of human agency and autonomy. It is most relevant during 2 - Post-deployment.

Weaponization

Weaponization is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most relevant duri...