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
3,021

AI/ML CVEs Tracked

424

Critical

114

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3021 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI GHSA-hf3c-wxg2-49q9 vLLM: DoS via unbounded XGrammar schema cache 6.5 — vllm Apr 15 CRIT E CVE-2025-32428 jupyter-remote-desktop-proxy: VNC network exposure — 0.9% jupyter-remote-desktop-proxy Apr 12 CRIT E CVE-2025-32375 BentoML: RCE via insecure deserialization in runner 9.8 50.4% bentoml Apr 9 MEDI CVE-2025-32381 xgrammar: unbounded grammar cache causes LLM server DoS 6.5 0.5% xgrammar Apr 9 MEDI GHSA-v7x6-rv5q-mhwc picklescan: bypass allows silent RCE in ML pipelines — — picklescan Apr 7 MEDI GHSA-fj43-3qmq-673f picklescan: numpy bypass enables RCE in ML model pipelines — — picklescan Apr 7 HIGH E CVE-2025-46417 picklescan: scanner bypass enables DNS data exfiltration — 0.2% picklescan Apr 7 CRIT CVE-2025-3248 Langflow: Unauth RCE via code injection endpoint 9.8 100.0% langflow Apr 7 CRIT E CVE-2025-27520 BentoML: unauthenticated RCE via insecure deserialization 9.8 35.7% bentoml Apr 4 HIGH E CVE-2025-30370 jupyterlab-git: command injection via malicious repo name 7.4 0.6% jupyterlab-git Apr 4 LOW E CVE-2025-3136 PyTorch: memory corruption in CUDA caching allocator 3.3 0.3% pytorch Apr 3 MEDI E CVE-2025-3121 PyTorch: memory corruption in JIT flatbuffer loader 5.5 0.3% pytorch Apr 2 MEDI CVE-2025-31843 OpenAI WP Plugin: broken access control on AI settings 4.3 0.4% — Apr 1 MEDI E CVE-2025-3001 PyTorch: lstm_cell memory corruption, local code exec 5.3 0.2% torch Mar 31 MEDI E CVE-2025-3000 PyTorch: memory corruption in torch.jit.script compiler 5.3 0.2% torch Mar 31 MEDI E CVE-2025-2999 PyTorch: memory corruption in RNN sequence unpacking 5.3 0.2% torch Mar 31 MEDI E CVE-2025-2998 PyTorch: memory corruption in RNN pad_packed_sequence 5.3 0.2% torch Mar 31 MEDI E CVE-2025-2953 PyTorch: DoS via mkldnn_max_pool2d resource leak 5.5 0.2% pytorch Mar 30 MEDI E CVE-2025-26265 openairinterface5g: segfault enables DoS via crafted UE message 6.5 0.4% openairinterface5g Mar 27 HIGH CVE-2025-30358 Mesop: class pollution enables DoS and LLM jailbreak 8.1 0.6% — Mar 27

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