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
2,375

AI/ML CVEs Tracked

336

Critical

408

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 2375 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI E CVE-2021-29517 TensorFlow: Conv3D div-by-zero crashes ML processes 5.5 0.2% tensorflow May 14 MEDI E CVE-2021-29516 TensorFlow: null ptr deref crashes RaggedTensor ops 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29515 TensorFlow: NULL ptr deref in MatrixDiag ops (crash/RCE) 7.8 0.2% tensorflow May 14 HIGH E CVE-2021-29514 TensorFlow: heap buffer overflow in RaggedBincount op 7.8 0.2% tensorflow May 14 HIGH E CVE-2021-29513 TensorFlow: type confusion → null ptr deref (CVSS 7.8) 7.8 0.2% tensorflow May 14 MEDI E CVE-2021-29554 TensorFlow: divide-by-zero DoS in DenseCountSparseOutput 5.5 0.2% tensorflow May 14 HIGH E CVE-2021-29512 TensorFlow: heap buffer overflow in RaggedBincount op 7.8 0.2% tensorflow May 14 MEDI CVE-2021-28796 Qiita::Markdown: XSS in transformer components 6.1 0.8% — Mar 18 LOW CVE-2020-26270 TensorFlow: DoS via zero-length input to LSTM/GRU on CUDA 3.3 0.2% tensorflow Dec 10 HIGH E CVE-2020-26269 TensorFlow: OOB read in glob path matching causes DoS 7.5 0.7% tensorflow Dec 10 MEDI E CVE-2020-26268 TensorFlow: ImmutableConst segfault crashes Python interpreter 4.4 0.2% tensorflow Dec 10 HIGH E CVE-2020-26267 TensorFlow: OOB read in DataFormatVecPermute op 7.8 0.2% tensorflow Dec 10 MEDI E CVE-2020-26266 TensorFlow: uninitialized memory read via crafted SavedModel 5.3 0.2% tensorflow Dec 10 LOW E CVE-2020-26271 TensorFlow: OOB read on saved model load leaks heap addresses 3.3 0.2% tensorflow Dec 10 HIGH E CVE-2020-28975 scikit-learn: DoS via crafted SVM model deserialization 7.5 3.4% scikit-learn Nov 21 HIGH E CVE-2020-15266 TensorFlow: NaN-triggered DoS in crop_and_resize op 7.5 0.9% tensorflow Oct 21 HIGH E CVE-2020-15265 TensorFlow: OOB read DoS via invalid quantize axis 7.5 0.9% tensorflow Oct 21 HIGH E CVE-2020-15214 TensorFlow Lite: OOB write in segment sum, memory corruption risk 8.1 0.6% tensorflow Sep 25 MEDI E CVE-2020-15213 TensorFlow Lite: OOM DoS via crafted segment sum model 4.0 0.6% tensorflow Sep 25 HIGH E CVE-2020-15212 TensorFlow Lite: heap OOB write via segment sum op 8.6 0.6% tensorflow Sep 25

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