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
2,371

AI/ML CVEs Tracked

345

Critical

449

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 2371 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2021-37685 TensorFlow Lite: OOB read leaks heap memory in expand_dims 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37684 TensorFlow TFLite: DoS via division by zero in pooling 5.5 0.1% tensorflow Aug 12 MEDI CVE-2021-37683 TFLite: division by zero DoS in inference kernels 5.5 0.2% tensorflow Aug 12 HIGH CVE-2021-37682 TFLite: uninitialized quant params corrupt inference 7.1 0.2% tensorflow Aug 12 HIGH CVE-2021-37679 TensorFlow: heap over-read leaks memory via RaggedTensor 7.8 0.2% tensorflow Aug 12 HIGH E CVE-2021-37678 TensorFlow/Keras: RCE via YAML model deserialization 8.8 0.5% tensorflow Aug 12 MEDI CVE-2021-37677 TensorFlow: DoS via invalid Dequantize axis argument 5.5 0.1% tensorflow Aug 12 MEDI CVE-2021-37674 TensorFlow: DoS via MaxPoolGrad invalid tensor input 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37673 TensorFlow: MapStage CHECK-fail causes process DoS 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37672 TensorFlow: heap OOB read in SdcaOptimizerV2 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37670 TensorFlow: heap OOB read in sorting ops 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37669 TensorFlow: integer conversion DoS in NonMaxSuppression ops 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37668 TensorFlow: DoS via div-by-zero in UnravelIndex op 5.5 0.2% tensorflow Aug 12 HIGH CVE-2021-37665 TensorFlow MKL: null-ptr/heap-OOB in requantization ops 7.8 0.2% tensorflow Aug 12 HIGH CVE-2021-37663 TensorFlow: QuantizeV2 heap OOB/null-deref in quantization 7.8 0.2% tensorflow Aug 12 MEDI CVE-2021-37689 TensorFlow Lite: MLIR null ptr deref crashes inference 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37688 TensorFlow Lite: DoS via crafted TFLite model file 5.5 0.2% tensorflow Aug 12 MEDI CVE-2021-37686 TFLite: infinite loop DoS via crafted strided slice model 5.5 0.2% tensorflow Aug 12 HIGH CVE-2021-37681 TensorFlow Lite: null ptr deref crashes SVDF inference 7.8 0.2% tensorflow Aug 12 MEDI CVE-2021-37680 TFLite: division by zero crashes fully connected layers 5.5 0.2% tensorflow Aug 12

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