AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 485 results — High severity, no patchTensorFlow Serving: JSON recursion DoS on inference API
CVE-2025-0649 vLLM: pickle RCE in multi-node inference deployments
CVE-2025-30165 vLLM: DoS via quadratic multimodal tokenizer input
CVE-2025-46560 vLLM: ZeroMQ socket exposure enables DoS in multi-node
CVE-2025-30202 jupyterlab-git: command injection via malicious repo name
CVE-2025-30370 Mesop: class pollution enables DoS and LLM jailbreak
CVE-2025-30358 LiteLLM: Langfuse API key leak via error handling
CVE-2025-0330 open-webui: DoS via unauthenticated multipart parsing
GHSA-5ccf-884p-4jjq Open-WebUI: unauthenticated PDF endpoint enables DoS
CVE-2024-8053 open-webui: unauthenticated DoS via markdown parser
CVE-2024-7983 pytorch-lightning: unauthenticated DoS crashes LightningApp
CVE-2024-8020 open-webui: Stored XSS enables admin session hijack
CVE-2024-7990 open-webui: XSS enables admin session hijack via chat
CVE-2024-7053 Open WebUI: auth bypass exposes all user files
CVE-2024-7043 open-webui: Privilege bypass enables admin account deletion
CVE-2024-7039 open-webui: unauthenticated DoS disables Admin panel
CVE-2024-7036 LiteLLM: RCE via post_call_rules callback injection
CVE-2024-6825 open-webui: DoS via starlette memory exhaustion
GHSA-w466-2wfc-8g58 open-webui: unauthenticated DoS via login payload flood
CVE-2024-12534 BentoML: DoS via multipart boundary in Gradio login
GHSA-hh3j-9m59-p8vc 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
AI Threat Alert