AI Threat AlertAI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 4307 resultsCVE-2021-29526TensorFlow: Conv2D divide-by-zero crashes ML workloads5.50.2%tensorflowMay 14HIGHECVE-2021-29525TensorFlow: div-by-zero DoS in Conv2DBackpropInput7.80.2%tensorflowMay 14MEDIECVE-2021-29524TensorFlow: div-by-zero DoS in Conv2D backprop op5.50.2%tensorflowMay 14MEDIECVE-2021-29523TensorFlow: DoS via integer overflow in sparse ops5.50.2%tensorflowMay 14MEDIECVE-2021-29522TensorFlow: Conv3DBackprop div-by-zero crashes training5.50.2%tensorflowMay 14MEDIECVE-2021-29521TensorFlow: DoS crash via negative sparse tensor shape5.50.2%tensorflowMay 14HIGHECVE-2021-29520TensorFlow: heap buffer overflow in Conv3DBackprop ops7.80.2%tensorflowMay 14MEDIECVE-2021-29519TensorFlow SparseCross: type confusion DoS5.50.2%tensorflowMay 14HIGHECVE-2021-29518TensorFlow: null ptr deref in session ops, local RCE7.80.2%tensorflowMay 14MEDIECVE-2021-29517TensorFlow: Conv3D div-by-zero crashes ML processes5.50.2%tensorflowMay 14MEDIECVE-2021-29516TensorFlow: null ptr deref crashes RaggedTensor ops5.50.2%tensorflowMay 14HIGHECVE-2021-29515TensorFlow: NULL ptr deref in MatrixDiag ops (crash/RCE)7.80.2%tensorflowMay 14HIGHECVE-2021-29514TensorFlow: heap buffer overflow in RaggedBincount op7.80.2%tensorflowMay 14HIGHECVE-2021-29513TensorFlow: type confusion → null ptr deref (CVSS 7.8)7.80.2%tensorflowMay 14MEDIECVE-2021-29554TensorFlow: divide-by-zero DoS in DenseCountSparseOutput5.50.2%tensorflowMay 14HIGHECVE-2021-29512TensorFlow: heap buffer overflow in RaggedBincount op7.80.2%tensorflowMay 14MEDICVE-2021-28796Qiita::Markdown: XSS in transformer components6.10.8%—Mar 18UNKNECVE-2020-35276EgavilanMedia ECM: SQLi bypasses admin login panel—1.6%—Dec 21LOWCVE-2020-26270TensorFlow: DoS via zero-length input to LSTM/GRU on CUDA3.30.2%tensorflowDec 10HIGHECVE-2020-26269TensorFlow: OOB read in glob path matching causes DoS7.50.7%tensorflowDec 10Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
Need deeper analysis?
Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.
Start 14-Day Free Trial