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 943 results — High severity, Active exploitationTensorFlow: heap OOB read/write enables network RCE
CVE-2022-23574TensorFlow: uninitialized memory in AssignOp
CVE-2022-23573TensorFlow: heap OOB write in Grappler, RCE risk
CVE-2022-23566TFLite: OOB read/write in sparse tensor → RCE
CVE-2022-23560TFLite: integer overflow in embedding lookup → heap OOB RW
CVE-2022-23559TFLite: integer overflow in model loading, RCE risk
CVE-2022-23558TensorFlow: heap overflow in sparse ops, RCE risk
CVE-2022-21740TensorFlow: OOB read leaks heap memory, enables DoS
CVE-2022-21730TensorFlow: heap OOB read in ReverseSequence op
CVE-2022-21728TensorFlow: Dequantize integer overflow, RCE risk
CVE-2022-21727TensorFlow: heap OOB read in Dequantize op allows RCE
CVE-2022-21726pytorch-lightning: deserialization RCE via malicious checkpoint
CVE-2021-4118Gradio: path traversal exposes host filesystem to users
CVE-2021-43831Sockeye: unsafe YAML load RCE via model config file
CVE-2021-43811TensorFlow: eval() in saved_model_cli allows RCE
CVE-2021-41228TensorFlow Grappler: uninitialized var, local priv-esc
CVE-2021-41225TensorFlow: CuDNN heap overflow, local code execution
CVE-2021-41221TensorFlow: use-after-free in async collective ops
CVE-2021-41220TensorFlow: heap overflow in Transpose via negative perm
CVE-2021-41216TensorFlow: heap R/W + DoS in boosted trees APIs
CVE-2021-41208Frequently 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