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
2,377

AI/ML CVEs Tracked

337

Critical

391

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 2377 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2022-36027 TensorFlow: DoS crash in transposed conv quantization 7.5 0.6% tensorflow Sep 16 HIGH E CVE-2022-36017 TensorFlow: DoS via malformed Requantize tensors 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-36016 TensorFlow: CHECK-fail assertion crashes model serving 7.5 0.5% tensorflow Sep 16 HIGH CVE-2022-36015 TensorFlow: integer overflow in RangeSize causes DoS 7.5 0.5% tensorflow Sep 16 HIGH CVE-2022-36014 TensorFlow: null ptr dereference in MLIR causes remote DoS 7.5 0.5% tensorflow Sep 16 HIGH CVE-2022-36013 TensorFlow MLIR: null ptr deref crashes model serving 7.5 0.5% tensorflow Sep 16 HIGH CVE-2022-36012 TensorFlow: DoS via empty MLIR function attributes 7.5 0.5% tensorflow Sep 16 HIGH CVE-2022-36011 TensorFlow: null deref DoS in MLIR function conversion 7.5 0.4% tensorflow Sep 16 HIGH E CVE-2022-36005 TensorFlow: DoS via CHECK fail in fake_quant gradient 7.5 0.4% tensorflow Sep 16 HIGH E CVE-2022-36004 TensorFlow: DoS via tf.random.gamma CHECK assertion 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-36003 TensorFlow: DoS via RandomPoissonV2 large input 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-36002 TensorFlow: DoS via Unbatch assertion failure 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-36001 TensorFlow: DoS via type confusion in DrawBoundingBoxes 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-36000 TensorFlow: null deref crashes MLIR graph conversion 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-35999 TensorFlow: DoS via empty Conv2DBackpropInput tensors 7.5 0.4% tensorflow Sep 16 HIGH E CVE-2022-35998 TensorFlow: DoS via EmptyTensorList CHECK fail 7.5 0.4% tensorflow Sep 16 HIGH E CVE-2022-35997 TensorFlow: CHECK-fail DoS in tf.sparse.cross op 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-35996 TensorFlow: Conv2D DoS via empty input tensor 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-35995 TensorFlow: DoS via AudioSummaryV2 CHECK failure 7.5 0.4% tensorflow Sep 16 HIGH CVE-2022-35994 TensorFlow: CollectiveGather assertion DoS via scalar 7.5 0.4% tensorflow Sep 16

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