archive

All Records

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

Showing 1461-1480 of 3623 records

ML Model Evaluation AI Mitigations

ML Model Evaluation groups 10 AI defenses for the AI lifecycle.

AI Artifacts - AI Security Technique

AI Artifacts is AI attack method AML.T0112.001 with evidence level: feasible.

Resource-Intensive Queries - AI Security Technique

Resource-Intensive Queries is AI attack method AML.T0034.001 with evidence level: feasible.

Excessive Queries - AI Security Technique

Excessive Queries is AI attack method AML.T0034.000 with evidence level: feasible.

Serverless - AI Security Technique

Serverless is AI attack method AML.T0008.004 with evidence level: feasible.

Technical Blogs - AI Security Technique

Technical Blogs is AI attack method AML.T0000.002 with evidence level: feasible.

Journals and Conference Proceedings - AI Security Technique

Journals and Conference Proceedings is AI attack method AML.T0000.000 with evidence level: feasible.

Memory Hardening - AI Mitigation

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

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)

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

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

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

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

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

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

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

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

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)

General Evaluations (Limited coverage of capabilities evaluations) is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. I...

Privacy

Privacy is an AI risk in 2. Privacy & Security focused on 2.0 > Privacy & Security. It is most relevant during 3 - Other.