archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1461-1480 of 3623 records
ML Model Evaluation groups 10 AI defenses for the AI lifecycle.
AI Artifacts is AI attack method AML.T0112.001 with evidence level: feasible.
Resource-Intensive Queries is AI attack method AML.T0034.001 with evidence level: feasible.
Excessive Queries is AI attack method AML.T0034.000 with evidence level: feasible.
Serverless is AI attack method AML.T0008.004 with evidence level: feasible.
Technical Blogs is AI attack method AML.T0000.002 with evidence level: feasible.
Journals and Conference Proceedings is AI attack method AML.T0000.000 with evidence level: feasible.
Memory Hardening is an AI mitigation for ML Model Engineering, Deployment, Monitoring and Maintenance, grouped as Technical - ML. It is connected to 2 attack...
Second-Order Risks is an AI risk in 6. Socioeconomic and Environmental focused on 6.0 > Socioeconomic & Environmental. It is most relevant during 2 - Post-de...
Cyberspace risks (Risks of confusing facts, misleading users, and bypassing authentication) is an AI risk in 3. Misinformation focused on 3.1 > False or misl...
Privacy and Property is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. I...
Personal data is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It is mo...
Income inequality and monopolies is an AI risk in 6. Socioeconomic and Environmental focused on 6.2 > Increased inequality and decline in employment quality...
Misinformation is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 2 - Post-deployment.
Confidentiality loss is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. I...
Broadly-Scoped Goals is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most relevant...
Privacy is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It is most rel...
AI System bypassing a sandbox environment is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities...
General Evaluations (Limited coverage of capabilities evaluations) is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. I...
Privacy is an AI risk in 2. Privacy & Security focused on 2.0 > Privacy & Security. It is most relevant during 3 - Other.