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-2022-23580 TensorFlow: uncontrolled allocation DoS in shape inference 6.5 0.8% tensorflow Feb 4 MEDI E CVE-2022-23579 TensorFlow: DoS via Grappler optimizer CHECK failure 6.5 0.8% tensorflow Feb 4 MEDI E CVE-2022-23578 TensorFlow: memory leak via invalid graph node 4.3 0.7% tensorflow Feb 4 MEDI E CVE-2022-23577 TensorFlow: null pointer deref crashes model loader 6.5 0.8% tensorflow Feb 4 MEDI E CVE-2022-23576 TensorFlow: integer overflow in cost estimator causes DoS 6.5 0.8% tensorflow Feb 4 MEDI E CVE-2022-23575 TensorFlow: integer overflow in cost estimator → DoS 6.5 0.8% tensorflow Feb 4 HIGH E CVE-2022-23574 TensorFlow: heap OOB read/write enables network RCE 8.8 0.8% tensorflow Feb 4 HIGH E CVE-2022-23573 TensorFlow: uninitialized memory in AssignOp 8.8 0.7% tensorflow Feb 4 MEDI E CVE-2022-23572 TensorFlow: DoS via shape inference assertion failure 6.5 1.0% tensorflow Feb 4 MEDI CVE-2022-23571 TensorFlow: protobuf assertion DoS via invalid tensor dtype 6.5 0.5% tensorflow Feb 4 MEDI E CVE-2022-23570 TensorFlow: null-deref DoS via malformed protobuf tensor 6.5 0.9% tensorflow Feb 4 HIGH E CVE-2022-23566 TensorFlow: heap OOB write in Grappler, RCE risk 8.8 0.9% tensorflow Feb 4 MEDI CVE-2022-23565 TensorFlow: DoS via malicious SavedModel AttrDef duplication 6.5 0.5% tensorflow Feb 4 MEDI CVE-2022-23564 TensorFlow: DoS via reachable assertion in protobuf decode 6.5 0.5% tensorflow Feb 4 MEDI CVE-2022-23563 TensorFlow: TOC/TOU race allows temp file hijacking 6.3 0.1% tensorflow Feb 4 HIGH CVE-2022-23562 TensorFlow: Range integer overflow, RCE/DoS risk 8.8 0.6% tensorflow Feb 4 HIGH CVE-2022-23561 TensorFlow Lite: OOB write, arbitrary write primitive 8.8 0.5% tensorflow Feb 4 HIGH E CVE-2022-23560 TFLite: OOB read/write in sparse tensor → RCE 8.8 0.8% tensorflow Feb 4 HIGH E CVE-2022-23559 TFLite: integer overflow in embedding lookup → heap OOB RW 8.8 1.2% tensorflow Feb 4 HIGH E CVE-2022-23558 TFLite: integer overflow in model loading, RCE risk 8.8 0.8% tensorflow Feb 4 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