archive
All Records
AI security records indexed from public vulnerability, risk, and attack datasets.
Showing 1521-1540 of 3706 records
LLM-Systems Can Be Untrustworthy is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.
Domain-Specific Misuses is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant during 2...
Agentic LLMs Pose Novel Risks is an AI risk in 7. AI System Safety, Failures, & Limitations focused on 7.2 > AI possessing dangerous capabilities. It is most...
Electoral interference is an AI risk in 4. Malicious Actors & Misuse focused on 4.1 > Disinformation, surveillance, and influence at scale. It is most releva...
Financial/earnings loss is an AI risk focused on X.1 > Excluded. It is most relevant during 2 - Post-deployment.
Confidentiality loss is an AI risk in 2. Privacy & Security focused on 2.0 > Privacy & Security. It is most relevant during 2 - Post-deployment.
Financial and business is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant during 2 -...
Defamation/libel/slander is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant during 2...
Reputational is an AI risk focused on X.1 > Excluded. It is most relevant during 3 - Other.
IP/copyright loss is an AI risk in 4. Malicious Actors & Misuse focused on 4.3 > Fraud, scams, and targeted manipulation. It is most relevant during 3 - Other.
CVE-2026-25253 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2025-8217 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2023-6021 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2023-6020 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2023-6019 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2023-48023 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2023-48022 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
CVE-2019-20634 is a vulnerability profile that is not currently listed by CISA as known exploited. It includes 1 related case study.
Reconnaissance is an ATLAS attacker goal with 8 related AI attack methods.
Impact is an ATLAS attacker goal with 9 related AI attack methods.