AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

76

New This Week

16

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 1604 results
Severity CVE ID Summary CVSS EPSS Package Date
LOW E CVE-2025-4287 PyTorch NCCL: local DoS in distributed training reduce op 3.3 0.1% — May 5 CRIT E CVE-2025-47241 browser-use: URL allowlist bypass enables SSRF in agents 9.3 0.2% browser-use May 5 HIGH E CVE-2025-46567 LLaMA-Factory: RCE via torch.load() unsafe deserialization 7.8 0.2% llamafactory May 1 HIGH E CVE-2025-46560 vLLM: DoS via quadratic multimodal tokenizer input 7.5 0.6% vllm Apr 30 CRIT E CVE-2025-32444 vLLM: RCE via pickle deserialization on ZeroMQ 9.8 2.5% vllm Apr 30 HIGH E CVE-2025-30202 vLLM: ZeroMQ socket exposure enables DoS in multi-node 7.5 0.4% vllm Apr 30 MEDI E CVE-2025-1194 transformers: ReDoS in GPT-NeoX Japanese tokenizer 6.5 0.1% transformers Apr 29 MEDI CVE-2025-46343 n8n: stored XSS enables account takeover 5.4 0.1% n8n Apr 29 CRIT GHSA-ggpf-24jw-3fcw vLLM: RCE via malicious model, PyTorch < 2.6 bypass 9.8 — vllm Apr 23 CRIT E CVE-2025-32434 PyTorch: RCE bypasses weights_only=True safe-load guard 9.8 1.2% pytorch Apr 18 MEDI E CVE-2025-3730 PyTorch: DoS via ctc_loss resource mishandling 5.5 0.1% pytorch Apr 16 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 — 0.2% jupyter-remote-desktop-proxy Apr 12 CRIT E CVE-2025-32375 BentoML: RCE via insecure deserialization in runner 9.8 67.3% bentoml Apr 9 MEDI CVE-2025-32381 xgrammar: unbounded grammar cache causes LLM server DoS 6.5 0.3% 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 91.8% langflow Apr 7 CRIT E CVE-2025-27520 BentoML: unauthenticated RCE via insecure deserialization 9.8 81.0% bentoml Apr 4

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