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 1092 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2025-46722 vLLM: image hash collision enables multimodal cache leakage 7.3 0.2% vllm May 29 LOW CVE-2025-46570 vLLM: timing side-channel leaks prompt cache data 2.6 0.2% vllm May 29 LOW E CVE-2025-5320 Gradio: CORS origin bypass in ML UI handler 3.7 0.1% gradio May 29 HIGH E CVE-2025-1753 llama-index-cli: OS command injection enables RCE 7.8 0.1% llama-index May 28 HIGH CVE-2025-5173 label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader 7.8 0.1% label-studio-ml May 26 CRIT E CVE-2025-47277 vLLM: RCE via exposed TCPStore in distributed inference 9.8 0.9% vllm May 20 HIGH E CVE-2025-2099 transformers: ReDoS in testing_utils causes DoS 7.5 0.1% transformers May 19 UNKN E CVE-2025-1975 Ollama: DoS via malicious manifest in /api/pull — 0.5% ollama May 16 HIGH CVE-2025-0649 TensorFlow Serving: JSON recursion DoS on inference API 7.5 0.1% tensorflow_serving May 6 HIGH CVE-2025-30165 vLLM: pickle RCE in multi-node inference deployments 8.0 1.3% vllm May 6 LOW E CVE-2025-4287 PyTorch NCCL: local DoS in distributed training reduce op 3.3 0.1% — May 5 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 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 CRIT E CVE-2025-32375 BentoML: RCE via insecure deserialization in runner 9.8 67.3% bentoml Apr 9 CRIT CVE-2025-3248 Langflow: Unauth RCE via code injection endpoint 9.8 91.8% langflow Apr 7

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