AI Threat AlertAI 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 4307 resultsCVE-2022-23564TensorFlow: DoS via reachable assertion in protobuf decode6.50.5%tensorflowFeb 4MEDICVE-2022-23563TensorFlow: TOC/TOU race allows temp file hijacking6.30.1%tensorflowFeb 4HIGHCVE-2022-23562TensorFlow: Range integer overflow, RCE/DoS risk8.80.6%tensorflowFeb 4HIGHCVE-2022-23561TensorFlow Lite: OOB write, arbitrary write primitive8.80.5%tensorflowFeb 4HIGHECVE-2022-23560TFLite: OOB read/write in sparse tensor → RCE8.80.8%tensorflowFeb 4HIGHECVE-2022-23559TFLite: integer overflow in embedding lookup → heap OOB RW8.81.2%tensorflowFeb 4HIGHECVE-2022-23558TFLite: integer overflow in model loading, RCE risk8.80.8%tensorflowFeb 4MEDIECVE-2022-23557TensorFlow TFLite: DoS via divide-by-zero in BiasAndClamp6.50.8%tensorflowFeb 4MEDIECVE-2022-21741TensorFlow Lite: DoS via crafted depthwise conv model6.50.8%tensorflowFeb 3HIGHECVE-2022-21740TensorFlow: heap overflow in sparse ops, RCE risk8.80.8%tensorflowFeb 3MEDIECVE-2022-21739TensorFlow: QuantizedMaxPool null ptr deref causes DoS6.50.8%tensorflowFeb 3MEDIECVE-2022-21738TensorFlow: integer overflow crashes process via sparse op6.50.8%tensorflowFeb 3MEDIECVE-2022-21737TensorFlow: DoS via malformed Bincount arguments6.50.8%tensorflowFeb 3MEDICVE-2022-23569TensorFlow: DoS via reachable assertions in ML ops6.50.5%tensorflowFeb 3MEDIECVE-2022-21735TensorFlow: DoS via FractionalMaxPool div-by-zero6.50.8%tensorflowFeb 3MEDIECVE-2022-21734TensorFlow: DoS via MapStage non-scalar key crash6.50.8%tensorflowFeb 3MEDIECVE-2022-21729TensorFlow: UnravelIndex integer overflow → DoS6.50.8%tensorflowFeb 3MEDIECVE-2022-21725TensorFlow: DoS via div-by-zero in conv cost estimator6.50.8%tensorflowFeb 3MEDIECVE-2022-23568TensorFlow: integer overflow DoS in sparse tensor ops6.50.8%tensorflowFeb 3MEDIECVE-2022-23567TensorFlow: integer overflow DoS in sparse tensor ops6.51.1%tensorflowFeb 3Frequently 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