All Records

Generate Deepfakes - AI Security Technique

Generate Deepfakes is AI attack method AML.T0088 with evidence level: realized. It includes 2 mitigations; 2 case studies; 9 related AI risks.

Phishing - AI Security Technique

Phishing is AI attack method AML.T0052 with evidence level: realized. It includes 2 mitigations; 2 case studies; 9 related AI risks.

Triggered - AI Security Technique

Triggered is AI attack method AML.T0051.002 with evidence level: demonstrated. It includes 2 mitigations; 2 case studies; 12 related AI risks.

Data - AI Security Technique

Data is AI attack method AML.T0010.002 with evidence level: realized. It includes 4 mitigations; 2 case studies; 10 related AI risks.

2.2 > AI system security vulnerabilities and attacks AI Risks

2.2 > AI system security vulnerabilities and attacks groups 108 AI risk records under 2. Privacy & Security.

Memory - AI Security Technique

Memory is AI attack method AML.T0080.000 with evidence level: demonstrated. It includes 1 mitigation; 2 case studies; 13 related AI risks.

Poison Training Data - AI Security Technique

Poison Training Data is AI attack method AML.T0020 with evidence level: realized. It includes 6 mitigations; 3 case studies; 6 related AI risks.

Information Security

Information Security is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most releva...

Evasion Attacks

Evasion Attacks is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 1 - Pre-de...

Risks to privacy

Risks to 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...

Valid Accounts - AI Security Technique

Valid Accounts is AI attack method AML.T0012 with evidence level: realized. It includes 8 case studies.

Adversarial input

Adversarial input 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...

7.3 > Lack of capability or robustness AI Risks

7.3 > Lack of capability or robustness groups 114 AI risk records under 7. AI System Safety, Failures, & Limitations.

Model weight leak

Model weight leak 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...

AI Intellectual Property Theft - AI Security Technique

AI Intellectual Property Theft is AI attack method AML.T0048.004 with evidence level: realized. It includes 3 mitigations; 5 case studies; 5 related AI risks.

Extraction attack

Extraction attack 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...

AI Agent Tool Data Poisoning - AI Security Technique

AI Agent Tool Data Poisoning is AI attack method AML.T0099 with evidence level: feasible. It includes 22 related AI risks.

Exploit Public-Facing Application - AI Security Technique

Exploit Public-Facing Application is AI attack method AML.T0049 with evidence level: realized. It includes 5 case studies; 1 related vulnerability.

Agentic Resource Consumption - AI Security Technique

Agentic Resource Consumption is AI attack method AML.T0034.002 with evidence level: feasible. It includes 22 related AI risks.

LLM Prompt Injection - AI Security Technique

LLM Prompt Injection is AI attack method AML.T0051 with evidence level: realized. It includes 6 mitigations; 1 case study; 12 related AI risks.