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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 2375 results CVE-2022-21726 TensorFlow: heap OOB read in Dequantize op allows RCE 8.8 0.8% tensorflow Feb 3 HIGH E CVE-2021-4118 pytorch-lightning: deserialization RCE via malicious checkpoint 7.8 1.0% pytorch_lightning Dec 23 HIGH E CVE-2021-43831 Gradio: path traversal exposes host filesystem to users 7.7 3.8% gradio Dec 15 HIGH E CVE-2021-43811 Sockeye: unsafe YAML load RCE via model config file 7.8 2.4% — Dec 8 HIGH CVE-2021-41134 nbdime: stored XSS in Jupyter notebook diff viewer 8.7 0.7% — Nov 8 HIGH E CVE-2021-41228 TensorFlow: eval() in saved_model_cli allows RCE 7.8 0.2% tensorflow Nov 5 MEDI E CVE-2021-41227 TensorFlow: OOB read in ImmutableConst leaks memory 5.5 0.2% tensorflow Nov 5 HIGH E CVE-2021-41225 TensorFlow Grappler: uninitialized var, local priv-esc 7.8 0.2% tensorflow Nov 5 MEDI E CVE-2021-41222 TensorFlow: SplitV negative arg segfault crashes process 5.5 0.2% tensorflow Nov 5 HIGH E CVE-2021-41221 TensorFlow: CuDNN heap overflow, local code execution 7.8 0.2% tensorflow Nov 5 HIGH E CVE-2021-41220 TensorFlow: use-after-free in async collective ops 7.8 0.2% tensorflow Nov 5 HIGH E CVE-2021-41216 TensorFlow: heap overflow in Transpose via negative perm 7.8 0.2% tensorflow Nov 5 MEDI E CVE-2021-41213 TensorFlow: tf.function deadlock enables DoS via model load 5.5 0.2% tensorflow Nov 5 MEDI CVE-2021-41218 TensorFlow: AllToAll DoS via divide-by-zero crash 5.5 0.1% tensorflow Nov 5 MEDI E CVE-2021-41209 TensorFlow: DoS via division-by-zero in conv ops 5.5 0.1% tensorflow Nov 5 HIGH E CVE-2021-41208 TensorFlow: heap R/W + DoS in boosted trees APIs 7.8 0.2% tensorflow Nov 5 MEDI E CVE-2021-41207 TensorFlow: ParallelConcat div-by-zero crashes ML process 5.5 0.1% tensorflow Nov 5 HIGH E CVE-2021-41206 TensorFlow: missing shape validation allows heap R/W 7.8 0.2% tensorflow Nov 5 MEDI E CVE-2021-41202 TensorFlow tf.range: integer overflow in kernel causes DoS 5.5 0.2% tensorflow Nov 5 HIGH E CVE-2021-41226 TensorFlow: heap OOB in SparseBinCount, crash/disclosure 7.1 0.2% tensorflow Nov 5 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