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 766 results — Active exploitation, no patchPyTorch: lstm_cell memory corruption, local code exec
CVE-2025-3001 PyTorch: memory corruption in torch.jit.script compiler
CVE-2025-3000 PyTorch: memory corruption in RNN sequence unpacking
CVE-2025-2999 PyTorch: memory corruption in RNN pad_packed_sequence
CVE-2025-2998 PyTorch: DoS via mkldnn_max_pool2d resource leak
CVE-2025-2953 openairinterface5g: segfault enables DoS via crafted UE message
CVE-2025-26265 InvokeAI: RCE via unsafe torch.load deserialization
CVE-2024-12029 LiteLLM: Langfuse API key leak via error handling
CVE-2025-0330 open-webui: Stored XSS enables admin session hijack
CVE-2024-7990 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: CSRF wipes RAG DB and AI memories via GET
CVE-2024-7035 open-webui: XSS enables admin session hijack via chat
CVE-2024-7053 open-webui: missing authz exposes admin prompts
CVE-2024-7045 Open WebUI: missing authz leaks admin credentials
CVE-2024-7046 open-webui: path traversal allows file write and RCE
CVE-2024-7033 Open WebUI: auth bypass exposes all user files
CVE-2024-7043 LiteLLM: RCE via post_call_rules callback injection
CVE-2024-6825 open-webui: unauthenticated DoS disables Admin panel
CVE-2024-7036 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