archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1601-1620 of 3623 records
Copyright Violation is an AI risk in 6. Socioeconomic and Environmental focused on 6.3 > Economic and cultural devaluation of human effort. It is most releva...
Deepfake Detection is an AI mitigation for Deployment, Monitoring and Maintenance, ML Model Evaluation, ML Model Engineering, grouped as Technical - ML. It i...
AI Agent Tools Permissions Configuration is an AI mitigation for Deployment, grouped as Technical - Cyber. It is connected to 5 attack methods.
Maintain AI Dataset Provenance is an AI mitigation for Data Preparation, Business and Data Understanding, grouped as Technical - ML. It is connected to 5 att...
Unhealthy or dangerous human-EAI relationships is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe use. It is most releva...
Misuse tactics to compromise GenAI systems (Data integrity) is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and at...
Insecurity 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...
Offensive cyber capabilities is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is mos...
Membership inference attack is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant durin...
Technical and operational risks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most r...
Terrorist access is an AI risk in 4. Malicious Actors & Misuse focused on 4.2 > Cyberattacks, weapon development or use, and mass harm. It is most relevant d...
Adversarial attacks targeting explainable AI techniques is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attack...
Memory and Storage 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...
Adversarial attack 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.
Privacy violations is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It...
Misuse tactics to compromise GenAI systems (Model integrity) is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or corr...
Strategic underperformance on model evaluations is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.1 > AI pursuing its own goals in c...
Adversarial Prompts is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most relevant during 2 - Po...
Direct Harm Domains (societal harm) is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
GPT-2 Model Replication - AI Case Study is an AI security case study covering type: exercise; target: OpenAI GPT-2; actor: Researchers at Brown University. I...