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-2022-29209TensorFlow: CHECK macro type confusion causes DoS5.50.4%tensorflowMay 21HIGHECVE-2022-29208TensorFlow: OOB write in EditDistance enables local DoS7.10.4%tensorflowMay 20MEDIECVE-2022-29206TensorFlow: SparseTensorDenseAdd null ptr deref DoS5.50.4%tensorflowMay 20MEDIECVE-2022-29205TensorFlow: NULL deref DoS via compat.v1 ops5.50.3%tensorflowMay 20MEDIECVE-2022-29204TensorFlow: DoS via UnsortedSegmentJoin input validation5.50.4%tensorflowMay 20MEDIECVE-2022-29203TensorFlow: DoS via SpaceToBatchND integer overflow5.50.3%tensorflowMay 20MEDIECVE-2022-29202TensorFlow: DoS via ragged tensor memory exhaustion5.50.3%tensorflowMay 20MEDIECVE-2022-29201TensorFlow: QuantizedConv2D null deref crashes model server5.50.3%tensorflowMay 20MEDIECVE-2022-29207TensorFlow: null-ptr deref in eager mode causes DoS5.50.3%tensorflowMay 20MEDIECVE-2022-29200TensorFlow: LSTMBlockCell DoS via invalid tensor rank5.50.3%tensorflowMay 20MEDIECVE-2022-29199TensorFlow: CHECK-fail DoS in LoadAndRemapMatrix op5.50.3%tensorflowMay 20MEDIECVE-2022-29198TensorFlow: DoS via sparse tensor input validation failure5.50.3%tensorflowMay 20MEDIECVE-2022-29197TensorFlow: DoS via UnsortedSegmentJoin input validation5.50.3%tensorflowMay 20MEDIECVE-2022-29196TensorFlow: DoS via invalid Conv3D filter input5.50.3%tensorflowMay 20MEDIECVE-2022-29195TensorFlow: StagePeek DoS via unvalidated index scalar5.50.3%tensorflowMay 20MEDIECVE-2022-29193TensorFlow: DoS via TensorSummaryV2 input validation failure5.50.3%tensorflowMay 20MEDIECVE-2022-29194TensorFlow: DoS via malformed DeleteSessionTensor input5.50.3%tensorflowMay 20MEDIECVE-2022-29192TensorFlow: DoS via QuantizeAndDequantize input validation5.50.3%tensorflowMay 20MEDIECVE-2022-29191TensorFlow: DoS via GetSessionTensor input validation5.50.4%tensorflowMay 20HIGHECVE-2022-24770Gradio: CSV formula injection via flagging enables RCE8.81.3%gradioMar 17Frequently 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