category

AI Security Techniques

Ways AI systems can be attacked or misused, with examples and defenses.

Showing 41-60 of 170 records

Spearphishing via Social Engineering LLM - AI Security Technique

Spearphishing via Social Engineering LLM is AI attack method AML.T0052.000 with evidence level: demonstrated. It includes 2 mitigations; 1 case study.

Discover AI Model Ontology - AI Security Technique

Discover AI Model Ontology is AI attack method AML.T0013 with evidence level: demonstrated. It includes 2 mitigations; 1 case study.

Train Proxy via Gathered AI Artifacts - AI Security Technique

Train Proxy via Gathered AI Artifacts is AI attack method AML.T0005.000 with evidence level: demonstrated. It includes 2 mitigations; 1 case study.

Escape to Host - AI Security Technique

Escape to Host is AI attack method AML.T0105 with evidence level: demonstrated. It includes 2 case studies.

Deploy AI Agent - AI Security Technique

Deploy AI Agent is AI attack method AML.T0103 with evidence level: realized. It includes 1 case study.

Generate Malicious Commands - AI Security Technique

Generate Malicious Commands is AI attack method AML.T0102 with evidence level: realized. It includes 1 case study.

AI Service API - AI Security Technique

AI Service API is AI attack method AML.T0096 with evidence level: realized. It includes 1 case study.

Manipulate User LLM Chat History - AI Security Technique

Manipulate User LLM Chat History is AI attack method AML.T0092 with evidence level: demonstrated. It includes 2 case studies.

Credentials from AI Agent Configuration - AI Security Technique

Credentials from AI Agent Configuration is AI attack method AML.T0083 with evidence level: demonstrated. It includes 2 case studies.

Corrupt AI Model - AI Security Technique

Corrupt AI Model is AI attack method AML.T0076 with evidence level: realized. It includes 1 case study.

Cloud Service Discovery - AI Security Technique

Cloud Service Discovery is AI attack method AML.T0075 with evidence level: realized. It includes 1 case study.

System Instruction Keywords - AI Security Technique

System Instruction Keywords is AI attack method AML.T0069.001 with evidence level: demonstrated. It includes 2 case studies.

Special Character Sets - AI Security Technique

Special Character Sets is AI attack method AML.T0069.000 with evidence level: demonstrated. It includes 2 case studies.

Command and Scripting Interpreter - AI Security Technique

Command and Scripting Interpreter is AI attack method AML.T0050 with evidence level: demonstrated. It includes 2 case studies.

Data from Information Repositories - AI Security Technique

Data from Information Repositories is AI attack method AML.T0036 with evidence level: realized. It includes 1 case study.

Obtain Capabilities - AI Security Technique

Obtain Capabilities is AI attack method AML.T0016 with evidence level: realized. It includes 1 case study.

Consumer Hardware - AI Security Technique

Consumer Hardware is AI attack method AML.T0008.001 with evidence level: realized. It includes 1 case study.

Search Open AI Vulnerability Analysis - AI Security Technique

Search Open AI Vulnerability Analysis is AI attack method AML.T0001 with evidence level: demonstrated. It includes 2 case studies.

RAG Databases - AI Security Technique

RAG Databases is AI attack method AML.T0085.000 with evidence level: demonstrated. It includes 4 mitigations; 1 case study.

Discover LLM Hallucinations - AI Security Technique

Discover LLM Hallucinations is AI attack method AML.T0062 with evidence level: demonstrated. It includes 4 mitigations; 1 case study.