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-2022-35973TensorFlow: DoS via QuantizedMatMul input validation7.50.5%tensorflowSep 16HIGHECVE-2022-35972TensorFlow: DoS via QuantizedBiasAdd rank validation7.50.5%tensorflowSep 16HIGHECVE-2022-35971TensorFlow: DoS via invalid quantization tensor rank7.50.5%tensorflowSep 16HIGHECVE-2022-35970TensorFlow: DoS via malformed QuantizedInstanceNorm tensors7.50.5%tensorflowSep 16HIGHECVE-2022-35969TensorFlow: DoS via malformed Conv2DBackpropInput7.50.5%tensorflowSep 16HIGHECVE-2022-35968TensorFlow: DoS via AvgPoolGrad shape validation failure7.50.5%tensorflowSep 16HIGHECVE-2022-35967TensorFlow: DoS via QuantizedAdd tensor rank flaw7.50.5%tensorflowSep 16HIGHECVE-2022-35966TensorFlow: DoS via QuantizedAvgPool input validation7.50.5%tensorflowSep 16HIGHECVE-2022-35965TensorFlow: NULL deref DoS via empty tensor input7.50.5%tensorflowSep 16HIGHECVE-2022-35964TensorFlow: remote DoS via BlockLSTMGradV2 validation7.50.5%tensorflowSep 16HIGHECVE-2022-35963TensorFlow: DoS via FractionalAvgPoolGrad overflow7.50.5%tensorflowSep 16HIGHECVE-2022-35960TensorFlow: DoS via malformed TensorListReserve input7.50.7%tensorflowSep 16HIGHECVE-2022-35959TensorFlow: DoS via AvgPool3DGradOp input overflow7.50.5%tensorflowSep 16HIGHECVE-2022-35952TensorFlow: DoS via UnbatchGradOp assertion crash7.50.7%tensorflowSep 16HIGHECVE-2022-35935TensorFlow: DoS via SobolSample CHECK-failure7.50.5%tensorflowSep 16HIGHECVE-2022-35934TensorFlow: tf.reshape DoS via integer overflow7.50.5%tensorflowSep 16HIGHECVE-2022-29216TensorFlow CLI: eval() injection enables reverse shell7.80.5%tensorflowMay 21MEDIECVE-2022-29213TensorFlow: input validation DoS in FFT signal ops5.50.3%tensorflowMay 21MEDIECVE-2022-29212TensorFlow Lite: quantization assert crash (DoS)5.50.3%tensorflowMay 21MEDIECVE-2022-29211TensorFlow: NaN input crashes histogram op (CPU DoS)5.50.3%tensorflowMay 21Frequently 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