AI Security Techniques

Manipulate AI Model - AI Security Technique

Manipulate AI Model is AI attack method AML.T0018 with evidence level: realized. It includes 3 mitigations; 12 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; 12 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; 12 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.

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; 13 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; 12 related AI risks.

Generate Deepfakes - AI Security Technique

Generate Deepfakes is AI attack method AML.T0088 with evidence level: realized. It includes 2 mitigations; 2 case studies; 10 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; 10 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; 9 related AI risks.

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.

Valid Accounts - AI Security Technique

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

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.

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 21 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 21 related AI risks.