archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1601-1620 of 3706 records
Capabilities that could be used to reduce human control - Cyber offence is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI pos...
Association in LLMs is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It...
Technical - ML groups 16 AI defenses by defense type.
Deepfake-Assisted Phishing is AI attack method AML.T0052.001 with evidence level: feasible. It includes 2 mitigations.
Spamming AI System with Chaff Data is AI attack method AML.T0046 with evidence level: feasible. It includes 2 mitigations.
Cost Harvesting is AI attack method AML.T0034 with evidence level: feasible. It includes 2 mitigations.
7.0 > AI system safety, failures, & limitations groups 17 AI risk records under 7. AI System Safety, Failures, & Limitations.
1.3 > Unequal performance across groups groups 17 AI risk records under 1. Discrimination & Toxicity.
Privacy - Prompt Inversion Attack (PIA) is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most re...
Privacy - Data Extraction Attack (DEA) is an AI risk in 2. Privacy & Security focused on 2.2 > AI system security vulnerabilities and attacks. It is most rel...
Performance & Robustness is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.3 > Lack of capability or robustness. It is most relevant...
Missing requirements for the implemented hardware is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
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...
Intellectual Property (IP) Infringement is an AI risk in 6. Socioeconomic and Environmental focused on 6.3 > Economic and cultural devaluation of human effor...
Autonomous replication / self-proliferation is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabiliti...
IP information in prompt is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive informatio...
Reidentification is an AI risk in 2. Privacy & Security focused on 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information. It is...
Intellectual property rights is an AI risk in 6. Socioeconomic and Environmental focused on 6.3 > Economic and cultural devaluation of human effort. It is mo...
Unhelpful Uses is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant during 2 - Post-de...
Environmental risk is an AI risk in 6. Socioeconomic and Environmental focused on 6.6 > Environmental harm. It is most relevant during 1 - Pre-deployment.