All Records

Data governance

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

Erode Dataset Integrity - AI Security Technique

Erode Dataset Integrity is AI attack method AML.T0059 with evidence level: demonstrated. It includes 2 mitigations; 1 case study; 13 related AI risks.

7.1 > AI pursuing its own goals in conflict with human goals or values AI Risks

7.1 > AI pursuing its own goals in conflict with human goals or values groups 97 AI risk records under 7. AI System Safety, Failures, & Limitations.

Risks from data (Risks of improper content and poisoning in training data)

Risks from data (Risks of improper content and poisoning in training data) is an AI risk in 1. Discrimination & Toxicity focused on 1.2 > Exposure to toxic c...

Privacy and data collection concerns (data protection concerns)

Privacy and data collection concerns (data protection concerns) is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or c...

AI Artifact Collection - AI Security Technique

AI Artifact Collection is AI attack method AML.T0035 with evidence level: realized. It includes 4 mitigations; 3 case studies; 5 related AI risks.

Privacy

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

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...

Manipulate AI Model - AI Security Technique

Manipulate AI Model is AI attack method AML.T0018 with evidence level: realized. It includes 3 mitigations; 13 related AI risks.

AI Supply Chain Rug Pull - AI Security Technique

AI Supply Chain Rug Pull is AI attack method AML.T0109 with evidence level: realized. It includes 1 case study; 13 related AI risks.

Prompt Infiltration via Public-Facing Application - AI Security Technique

Prompt Infiltration via Public-Facing Application is AI attack method AML.T0093 with evidence level: demonstrated. It includes 8 case studies.

Unsecured Credentials - AI Security Technique

Unsecured Credentials is AI attack method AML.T0055 with evidence level: realized. It includes 7 case studies.

Domains - AI Security Technique

Domains is AI attack method AML.T0008.002 with evidence level: demonstrated. It includes 2 case studies; 13 related AI risks.

Verify Attack - AI Security Technique

Verify Attack is AI attack method AML.T0042 with evidence level: demonstrated. It includes 4 mitigations; 7 case studies.

Search Open Technical Databases - AI Security Technique

Search Open Technical Databases is AI attack method AML.T0000 with evidence level: demonstrated. It includes 1 mitigation; 8 case studies.

Organization Confusion on Hugging Face - AI Case Study

Organization Confusion on Hugging Face - AI Case Study is an AI security case study covering type: exercise; target: Hugging Face users; actor: threlfall_hax...

Security

Security is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 3 - Other.

AI Agent Tool Poisoning - AI Security Technique

AI Agent Tool Poisoning is AI attack method AML.T0110 with evidence level: realized. It includes 1 case study; 14 related AI risks.

Insert Backdoor Trigger - AI Security Technique

Insert Backdoor Trigger is AI attack method AML.T0043.004 with evidence level: demonstrated. It includes 5 mitigations; 1 case study; 13 related AI risks.

OpenClaw Command & Control via Prompt Injection - AI Case Study

OpenClaw Command & Control via Prompt Injection - AI Case Study is an AI security case study covering type: exercise; target: OpenClaw; actor: HiddenLayer. I...