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 patchGradio: zip bomb DoS via dataframe CSV upload
CVE-2024-10569 vLLM: RCE via unsafe deserialization in Mooncake KV
CVE-2025-29783 vLLM: DoS via unbounded grammar cache exhausts disk
CVE-2025-29770 Keras: safe_mode bypass enables RCE via model loading
CVE-2025-1550 PyTorch: improper init in quantized sigmoid skews model output
CVE-2025-2149 PyTorch: memory corruption in JIT profiler callback handler
CVE-2025-2148 picklescan: ZIP flag bypass enables RCE in PyTorch models
CVE-2025-1945 gpt_academic: symlink traversal exposes all server files
CVE-2025-25185 Gradio: ACL bypass via path case manipulation
CVE-2025-23042 Composio: command injection in AI agent tool calls
CVE-2024-53526 Keras: path traversal enables arbitrary file write
CVE-2024-55459 WP Text Prompter: Stored XSS in OpenAI shortcode plugin
CVE-2024-11896 Lobe Chat: pre-auth SSRF leaks OpenAI API keys
CVE-2024-32965 Transformers: RCE via Trax model deserialization
CVE-2024-11394 Transformers: RCE via MaskFormer model deserialization
CVE-2024-11393 HuggingFace Transformers: RCE via config deserialization
CVE-2024-11392 Intel Extension for Transformers: path traversal privesc
CVE-2024-21799 Gradio: path traversal exposes arbitrary server files
CVE-2024-51751 Langflow: RCE via unsandboxed code component execution
CVE-2024-48061 Gradio: SSRF in DownloadButton exposes internal resources
CVE-2024-48052 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