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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4307 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
UNKNCVE-2021-42059InsydeH2O: UEFI firmware stack overflow enables RCE—0.3%—Feb 3UNKNCVE-2021-43615InsydeH2O UEFI: SMM memory corruption escalates to Ring -2—0.3%—Feb 3UNKNCVE-2021-41841InsydeH2O: SMM callout allows arbitrary code execution—0.3%—Feb 3UNKNCVE-2020-5953InsydeH2O UEFI: SMM privilege escalation (not AI-related)—0.3%—Feb 3UNKNCVE-2022-24069InsydeH2O UEFI: SMM callout enables privilege escalation—0.3%—Feb 2UNKNCVE-2021-43522Insyde H2O: SMM memory corruption escalates privileges—0.3%—Feb 2UNKNCVE-2021-45971InsydeH2O firmware: unchecked SMM buffer enables ring -2 exploit—0.3%—Jan 5UNKNCVE-2021-45969InsydeH2O UEFI: SMM buffer flaw enables privesc—0.3%—Jan 5UNKNCVE-2021-45970InsydeH2O: SMM buffer validation flaw enables priv-esc—0.4%—Jan 5HIGHECVE-2021-4118pytorch-lightning: deserialization RCE via malicious checkpoint7.81.0%pytorch_lightningDec 23HIGHECVE-2021-43831Gradio: path traversal exposes host filesystem to users7.73.9%gradioDec 15HIGHECVE-2021-43811Sockeye: unsafe YAML load RCE via model config file7.82.5%—Dec 8HIGHCVE-2021-41134nbdime: stored XSS in Jupyter notebook diff viewer8.70.7%—Nov 8HIGHECVE-2021-41228TensorFlow: eval() in saved_model_cli allows RCE7.80.2%tensorflowNov 5MEDIECVE-2021-41227TensorFlow: OOB read in ImmutableConst leaks memory5.50.2%tensorflowNov 5HIGHECVE-2021-41225TensorFlow Grappler: uninitialized var, local priv-esc7.80.2%tensorflowNov 5MEDIECVE-2021-41222TensorFlow: SplitV negative arg segfault crashes process5.50.2%tensorflowNov 5HIGHECVE-2021-41221TensorFlow: CuDNN heap overflow, local code execution7.80.2%tensorflowNov 5HIGHECVE-2021-41220TensorFlow: use-after-free in async collective ops7.80.2%tensorflowNov 5HIGHECVE-2021-41216TensorFlow: heap overflow in Transpose via negative perm7.80.2%tensorflowNov 5

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