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

392

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 1551 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
MEDI E CVE-2021-29556 TensorFlow: DoS via divide-by-zero in Reverse op 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29555 TensorFlow: FusedBatchNorm divide-by-zero crashes ML jobs 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29553 TensorFlow: heap OOB read via malicious axis in quant op 7.1 0.2% tensorflow May 14 MEDI E CVE-2021-29552 TensorFlow: DoS via empty num_segments tensor assertion 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29551 TensorFlow: OOB read DoS in MatrixTriangularSolve kernel 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29550 TensorFlow: FractionalAvgPool DoS via divide-by-zero 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29549 TensorFlow: divide-by-zero DoS in quantized batch norm op 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29548 TensorFlow: DoS via division by zero in QuantizedBatchNorm 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29547 TensorFlow: OOB read DoS via empty tensor in QuantizedBatchNorm 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29546 TensorFlow: div-by-zero in QuantizedBiasAdd, C/I/A high 7.8 0.2% tensorflow May 14 MEDI E CVE-2021-29545 TensorFlow: heap OOB write in sparse tensor DoS 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29544 TensorFlow: DoS via missing tensor rank validation 5.5 0.3% tensorflow May 14 MEDI E CVE-2021-29543 TensorFlow: DoS via assertion fail in CTCGreedyDecoder 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29542 TensorFlow: StringNGrams heap overflow crashes ML process 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29541 TensorFlow: null ptr deref DoS in StringNGrams op 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29540 TensorFlow: heap buffer overflow in Conv2D gradient op 7.8 0.2% tensorflow May 14 MEDI E CVE-2021-29539 TensorFlow: type confusion in ImmutableConst causes DoS 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29538 TensorFlow: div-by-zero DoS in Conv2DBackpropFilter 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29537 TensorFlow: heap overflow in QuantizedResizeBilinear op 7.8 0.2% tensorflow May 14 HIGH E CVE-2021-29536 TensorFlow: heap overflow in QuantizedReshape op 7.8 0.2% tensorflow May 14

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