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 1561 results — no patch 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 MEDI E CVE-2022-23557 TensorFlow TFLite: DoS via divide-by-zero in BiasAndClamp 6.5 0.7% tensorflow Feb 4 MEDI E CVE-2022-21741 TensorFlow Lite: DoS via crafted depthwise conv model 6.5 0.8% tensorflow Feb 3 HIGH E CVE-2022-21740 TensorFlow: heap overflow in sparse ops, RCE risk 8.8 0.8% tensorflow Feb 3 MEDI E CVE-2022-21739 TensorFlow: QuantizedMaxPool null ptr deref causes DoS 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-21738 TensorFlow: integer overflow crashes process via sparse op 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-21737 TensorFlow: DoS via malformed Bincount arguments 6.5 0.8% tensorflow Feb 3 MEDI CVE-2022-23569 TensorFlow: DoS via reachable assertions in ML ops 6.5 0.5% tensorflow Feb 3 MEDI E CVE-2022-21735 TensorFlow: DoS via FractionalMaxPool div-by-zero 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-21734 TensorFlow: DoS via MapStage non-scalar key crash 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-21729 TensorFlow: UnravelIndex integer overflow → DoS 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-21725 TensorFlow: DoS via div-by-zero in conv cost estimator 6.5 0.8% tensorflow Feb 3 MEDI E CVE-2022-23568 TensorFlow: integer overflow DoS in sparse tensor ops 6.5 0.8% tensorflow Feb 3 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