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 2876 results — no patchCVE-2021-42952Zepl Notebooks: sandbox escape exposes cloud metadata—1.6%—Feb 25HIGHECVE-2022-0736MLflow: insecure temp file handling causes DoS7.51.6%mlflowFeb 23UNKNECVE-2022-23321XMPie UStore: persistent XSS in admin user panel—0.6%—Feb 10MEDIECVE-2022-23595TensorFlow XLA: null pointer dereference causes DoS6.50.8%tensorflowFeb 4MEDICVE-2022-23594TensorFlow MLIR: heap OOB via malicious SavedModel file5.50.1%tensorflowFeb 4HIGHECVE-2022-23593TensorFlow MLIR-TFRT: DoS via scalar shape segfault7.50.9%tensorflowFeb 4HIGHECVE-2022-23592TensorFlow: heap OOB read in type inference engine8.10.9%tensorflowFeb 4HIGHECVE-2022-23591TensorFlow: SavedModel stack overflow via recursive GraphDef7.50.8%tensorflowFeb 4HIGHECVE-2022-23590TensorFlow: DoS via malicious SavedModel GraphDef7.51.0%tensorflowFeb 4MEDIECVE-2022-23589TensorFlow Grappler: DoS via malicious SavedModel6.51.1%tensorflowFeb 4MEDIECVE-2022-23588TensorFlow: DoS via crafted SavedModel crashes Grappler6.50.9%tensorflowFeb 4CRITECVE-2022-23587TensorFlow: integer overflow in Grappler enables RCE9.80.9%tensorflowFeb 4MEDIECVE-2022-23586TensorFlow: SavedModel DoS crashes Python interpreter6.50.8%tensorflowFeb 4MEDIECVE-2022-23585TensorFlow: memory leak in PNG decode causes DoS6.51.0%tensorflowFeb 4MEDIECVE-2022-23584TensorFlow: use-after-free in PNG decode causes DoS6.50.7%tensorflowFeb 4MEDIECVE-2022-23583TensorFlow: SavedModel type confusion triggers DoS crash6.50.9%tensorflowFeb 4MEDIECVE-2022-23582TensorFlow: SavedModel CHECK-fail causes DoS6.50.8%tensorflowFeb 4MEDIECVE-2022-23581TensorFlow: DoS via Grappler optimizer CHECK failure6.51.2%tensorflowFeb 4MEDIECVE-2022-23580TensorFlow: uncontrolled allocation DoS in shape inference6.50.8%tensorflowFeb 4MEDIECVE-2022-23579TensorFlow: DoS via Grappler optimizer CHECK failure6.50.8%tensorflowFeb 4Frequently 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