AI Threat Alert

AI 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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
2,385

AI/ML CVEs Tracked

337

Critical

390

New This Week

18

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 1069 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
MEDI E CVE-2022-29203 TensorFlow: DoS via SpaceToBatchND integer overflow 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29202 TensorFlow: DoS via ragged tensor memory exhaustion 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29201 TensorFlow: QuantizedConv2D null deref crashes model server 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29207 TensorFlow: null-ptr deref in eager mode causes DoS 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29200 TensorFlow: LSTMBlockCell DoS via invalid tensor rank 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29199 TensorFlow: CHECK-fail DoS in LoadAndRemapMatrix op 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29198 TensorFlow: DoS via sparse tensor input validation failure 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29197 TensorFlow: DoS via UnsortedSegmentJoin input validation 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29196 TensorFlow: DoS via invalid Conv3D filter input 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29195 TensorFlow: StagePeek DoS via unvalidated index scalar 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29193 TensorFlow: DoS via TensorSummaryV2 input validation failure 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29194 TensorFlow: DoS via malformed DeleteSessionTensor input 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29192 TensorFlow: DoS via QuantizeAndDequantize input validation 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29191 TensorFlow: DoS via GetSessionTensor input validation 5.5 0.4% tensorflow May 20 HIGH E CVE-2022-24770 Gradio: CSV formula injection via flagging enables RCE 8.8 1.2% gradio Mar 17 CRIT E CVE-2022-0845 pytorch-lightning: code injection enables full RCE 9.8 1.0% pytorch_lightning Mar 5 HIGH E CVE-2022-0736 MLflow: insecure temp file handling causes DoS 7.5 1.6% mlflow Feb 23 MEDI E CVE-2022-23595 TensorFlow XLA: null pointer dereference causes DoS 6.5 0.8% tensorflow Feb 4 HIGH E CVE-2022-23593 TensorFlow MLIR-TFRT: DoS via scalar shape segfault 7.5 0.9% tensorflow Feb 4 HIGH E CVE-2022-23592 TensorFlow: heap OOB read in type inference engine 8.1 0.8% tensorflow Feb 4

Frequently 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