archive

All Records

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

Showing 1501-1520 of 3623 records

Defense Evasion - ATLAS Tactic

Defense Evasion is an ATLAS attacker goal with 15 related AI attack methods.

Restrict AI Agent Tool Invocation on Untrusted Data - AI Mitigation

Restrict AI Agent Tool Invocation on Untrusted Data is an AI mitigation for Deployment, grouped as Technical - ML. It is connected to 3 attack methods.

Human In-the-Loop for AI Agent Actions - AI Mitigation

Human In-the-Loop for AI Agent Actions is an AI mitigation for Deployment, grouped as Technical - ML. It is connected to 3 attack methods.

Vulnerability Scanning - AI Mitigation

Vulnerability Scanning is an AI mitigation for ML Model Engineering, Data Preparation, grouped as Technical - Cyber. It is connected to 3 attack methods.

Restrict Library Loading - AI Mitigation

Restrict Library Loading is an AI mitigation for Deployment, grouped as Technical - Cyber. It is connected to 3 attack methods.

Use Multi-Modal Sensors - AI Mitigation

Use Multi-Modal Sensors is an AI mitigation for Business and Data Understanding, Data Preparation, ML Model Engineering, grouped as Technical - Cyber. It is...

Environment - Pre-Deployment

Environment - Pre-Deployment is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.0 > AI system safety, failures, & limitations. It is...

Environmental harms from operating LMs

Environmental harms from operating LMs is an AI risk in 6. Socioeconomic and Environmental focused on 6.6 > Environmental harm. It is most relevant during 3...

Risks from data (Risks of data leakage)

Risks from data (Risks of data leakage) is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensi...

Reverse Exposure

Reverse Exposure 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-...

Verifiability

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

Transparency and explainability

Transparency and explainability is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.4 > Lack of transparency or interpretability. It i...

Benchmarking (Post-deployment contamination)

Benchmarking (Post-deployment contamination) is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. It is most relevant dur...

Extrinsic

Extrinsic is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.

Defamation

Defamation is an AI risk in 3. Misinformation focused on 3.1 > False or misleading information. It is most relevant during 2 - Post-deployment.

Entrenchment and exacerbation of existing inequalities

Entrenchment and exacerbation of existing inequalities is an AI risk in 6. Socioeconomic and Environmental focused on 6.1 > Power centralization and unfair d...

Privacy concerns

Privacy concerns is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most relevant during 2 - Post-deployment.

Capabilities that could be used to reduce human control - Cyber offence

Capabilities that could be used to reduce human control - Cyber offence is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI pos...

Association in LLMs

Association in LLMs is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It...

Technical - ML AI Mitigations

Technical - ML groups 16 AI defenses by defense type.