All Records

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.

Generative AI Guardrails - AI Mitigation

Generative AI Guardrails is an AI mitigation for ML Model Engineering, ML Model Evaluation, Deployment, grouped as Technical - ML. It is connected to 8 attac...

Code Signing - AI Mitigation

Code Signing is an AI mitigation for Deployment, grouped as Technical - Cyber. It is connected to 8 attack methods.

Input Restoration - AI Mitigation

Input Restoration is an AI mitigation for Data Preparation, ML Model Evaluation, Deployment, Monitoring and Maintenance, grouped as Technical - ML. It is con...

Validate AI Model - AI Mitigation

Validate AI Model is an AI mitigation for ML Model Evaluation, Monitoring and Maintenance, grouped as Technical - ML. It is connected to 8 attack methods.

Model Hardening - AI Mitigation

Model Hardening is an AI mitigation for Data Preparation, ML Model Engineering, grouped as Technical - ML. It is connected to 8 attack methods.

Attempted Evasion of ML Phishing Webpage Detection System - AI Case Study

Attempted Evasion of ML Phishing Webpage Detection System - AI Case Study is an AI security case study covering type: incident; target: Commercial ML Phishin...

7.4 > Lack of transparency or interpretability AI Risks

7.4 > Lack of transparency or interpretability groups 41 AI risk records under 7. AI System Safety, Failures, & Limitations.

Malicious use and abuse (cybercrime)

Malicious use and abuse (cybercrime) is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relev...

Novel Attacks on LLMs

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

Overhead Attacks

Overhead Attacks 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.

OpenClaw 1-Click Remote Code Execution - AI Case Study

OpenClaw 1-Click Remote Code Execution - AI Case Study is an AI security case study covering type: exercise; target: OpenClaw; actor: DepthFirst. It includes...

5.2 > Loss of human agency and autonomy AI Risks

5.2 > Loss of human agency and autonomy groups 42 AI risk records under 5. Human-Computer Interaction.

Malicious and Indirect

Malicious and Indirect is an AI risk in 4. Malicious Actors & Misuse focused on 4.0 > Malicious use. It is most relevant during 3 - Other.

Exposure

Exposure 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 re...

Confidential information in data

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

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.