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 1961 results — Active exploitationCVE-2021-29552TensorFlow: DoS via empty num_segments tensor assertion5.50.2%tensorflowMay 14MEDIECVE-2021-29551TensorFlow: OOB read DoS in MatrixTriangularSolve kernel5.50.2%tensorflowMay 14MEDIECVE-2021-29550TensorFlow: FractionalAvgPool DoS via divide-by-zero5.50.2%tensorflowMay 14MEDIECVE-2021-29549TensorFlow: divide-by-zero DoS in quantized batch norm op5.50.2%tensorflowMay 14MEDIECVE-2021-29548TensorFlow: DoS via division by zero in QuantizedBatchNorm5.50.2%tensorflowMay 14MEDIECVE-2021-29547TensorFlow: OOB read DoS via empty tensor in QuantizedBatchNorm5.50.2%tensorflowMay 14HIGHECVE-2021-29546TensorFlow: div-by-zero in QuantizedBiasAdd, C/I/A high7.80.2%tensorflowMay 14MEDIECVE-2021-29545TensorFlow: heap OOB write in sparse tensor DoS5.50.2%tensorflowMay 14MEDIECVE-2021-29544TensorFlow: DoS via missing tensor rank validation5.50.3%tensorflowMay 14MEDIECVE-2021-29543TensorFlow: DoS via assertion fail in CTCGreedyDecoder5.50.2%tensorflowMay 14MEDIECVE-2021-29542TensorFlow: StringNGrams heap overflow crashes ML process5.50.2%tensorflowMay 14MEDIECVE-2021-29541TensorFlow: null ptr deref DoS in StringNGrams op5.50.2%tensorflowMay 14HIGHECVE-2021-29540TensorFlow: heap buffer overflow in Conv2D gradient op7.80.2%tensorflowMay 14MEDIECVE-2021-29539TensorFlow: type confusion in ImmutableConst causes DoS5.50.2%tensorflowMay 14MEDIECVE-2021-29538TensorFlow: div-by-zero DoS in Conv2DBackpropFilter5.50.2%tensorflowMay 14HIGHECVE-2021-29537TensorFlow: heap overflow in QuantizedResizeBilinear op7.80.2%tensorflowMay 14HIGHECVE-2021-29536TensorFlow: heap overflow in QuantizedReshape op7.80.2%tensorflowMay 14HIGHECVE-2021-29535TensorFlow: heap overflow in QuantizedMul op7.80.2%tensorflowMay 14MEDIECVE-2021-29534TensorFlow: DoS via CHECK-fail in SparseConcat op5.50.2%tensorflowMay 14MEDIECVE-2021-29533TensorFlow: DoS via empty image in DrawBoundingBoxes5.50.2%tensorflowMay 14Frequently 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