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 943 results — High severity, Active exploitationTensorFlow: heap overflow in FusedBatchNorm risks RCE
CVE-2021-29583TensorFlow: OOB heap read via Dequantize shape mismatch
CVE-2021-29582TensorFlow: heap buffer overflow in MaxPoolGrad kernel
CVE-2021-29579TensorFlow: heap buffer overflow in FractionalAvgPoolGrad
CVE-2021-29578TensorFlow: heap overflow in AvgPool3DGrad op
CVE-2021-29577TensorFlow: heap buffer overflow in MaxPool3DGradGrad op
CVE-2021-29576TensorFlow: null ptr deref in MaxPool3DGradGrad ops
CVE-2021-29574TensorFlow: heap OOB write via crafted bounding box op
CVE-2021-29571TensorFlow: OOB read in MaxPoolGradWithArgmax op
CVE-2021-29570TensorFlow: OOB heap read in MaxPoolGradWithArgmax op
CVE-2021-29569TensorFlow: null deref in ParameterizedTruncatedNormal op
CVE-2021-29568TensorFlow: heap OOB write in Dilation2D training op
CVE-2021-29566TensorFlow: heap OOB in RaggedTensorToTensor op
CVE-2021-29560TensorFlow: heap OOB read in UnicodeEncode leaks memory
CVE-2021-29559TensorFlow: heap buffer overflow in SparseSplit op
CVE-2021-29558TensorFlow: heap OOB read via malicious axis in quant op
CVE-2021-29553TensorFlow: div-by-zero in QuantizedBiasAdd, C/I/A high
CVE-2021-29546TensorFlow: heap buffer overflow in Conv2D gradient op
CVE-2021-29540TensorFlow: heap overflow in QuantizedResizeBilinear op
CVE-2021-29537TensorFlow: heap overflow in QuantizedReshape op
CVE-2021-29536Frequently 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