archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1301-1320 of 3623 records
Privilege Escalation is an ATLAS attacker goal with 4 related AI attack methods.
Collection is an ATLAS attacker goal with 4 related AI attack methods.
AI Model Access is an ATLAS attacker goal with 4 related AI attack methods.
SesameOp: Novel backdoor uses OpenAI Assistants API for command and control - AI Case Study is an AI security case study covering type: incident; target: Ope...
3.0 > Misinformation groups 5 AI risk records under 3. Misinformation.
2.0 > Privacy & Security groups 6 AI risk records under 2. Privacy & Security.
1.0 > Discrimination & Toxicity groups 6 AI risk records under 1. Discrimination & Toxicity.
Credential Access is an ATLAS attacker goal with 6 related AI attack methods.
Exfiltration is an ATLAS attacker goal with 6 related AI attack methods.
Execution is an ATLAS attacker goal with 6 related AI attack methods.
AI Attack Staging is an ATLAS attacker goal with 6 related AI attack methods.
Policy groups 7 AI defenses by defense type.
Initial Access is an ATLAS attacker goal with 7 related AI attack methods.
Unfairness and Bias is an AI risk in 1. Discrimination & Toxicity focused on 1.0 > Discrimination & Toxicity. It is most relevant during 2 - Post-deployment.
Environment - Post-Deployment is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.0 > AI system safety, failures, & limitations. It is...
Social acceptance and trust in AI is an AI risk focused on X.1 > Excluded. It is most relevant during 4 - Not coded.
Governance of autonomous intelligence systems is an AI risk in 6. Socioeconomic and Environmental focused on 6.5 > Governance failure. It is most relevant du...
Security threats 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...
Anthropomorphising systems can lead to overreliance and unsafe use is an AI risk in 5. Human-Computer Interaction focused on 5.1 > Overreliance and unsafe us...
Making disinformation cheaper and more effective is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence a...