archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1541-1560 of 3623 records
Physical Health is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 2 - Post-deployment.
Coercion and Extortion is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.6 > Multi-agent risks. It is most relevant during 3 - Other.
Misinformation risks is an AI risk in 3. Misinformation focused on 3.0 > Misinformation. It is most relevant during 3 - Other.
Invert AI Model is AI attack method AML.T0024.001 with evidence level: feasible. It includes 3 mitigations.
Infer Training Data Membership is AI attack method AML.T0024.000 with evidence level: feasible. It includes 3 mitigations.
Discover AI Model Family is AI attack method AML.T0014 with evidence level: feasible. It includes 3 mitigations.
Security is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 2 - Post-deployment.
Disparate Performance is an AI risk in 1. Discrimination & Toxicity focused on 1.3 > Unequal performance across groups. It is most relevant during 3 - Other.
Inconsistency 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 2 -...
Indiscriminate Weapons (CBRNE) is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is m...
Legal challenges is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It is...
False Recall of Memorized Information is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 3 - Other.
Private Training Data is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information...
Environmental risk is an AI risk.
Use Alternate Authentication Material is AI attack method AML.T0091 with evidence level: demonstrated.
Discover AI Agent Configuration is AI attack method AML.T0084 with evidence level: demonstrated.
Discover LLM System Information is AI attack method AML.T0069 with evidence level: demonstrated.
Encrypt Sensitive Information is an AI mitigation for Data Preparation, ML Model Engineering, Deployment, grouped as Technical - Cyber. It is connected to 4...
Sanitize Training Data is an AI mitigation for Business and Data Understanding, Data Preparation, Monitoring and Maintenance, grouped as Technical - ML. It i...
Compromised PyTorch Dependency Chain - AI Case Study is an AI security case study covering type: incident; target: PyTorch; actor: Unknown. It includes 3 cas...