AI Threat AlertAI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1527 results — Medium severityCVE-2025-3730PyTorch: DoS via ctc_loss resource mishandling5.50.3%pytorchApr 16MEDIGHSA-hf3c-wxg2-49q9vLLM: DoS via unbounded XGrammar schema cache6.5—vllmApr 15MEDICVE-2025-32381xgrammar: unbounded grammar cache causes LLM server DoS6.50.5%xgrammarApr 9MEDIGHSA-v7x6-rv5q-mhwcpicklescan: bypass allows silent RCE in ML pipelines——picklescanApr 7MEDIGHSA-fj43-3qmq-673fpicklescan: numpy bypass enables RCE in ML model pipelines——picklescanApr 7MEDIECVE-2025-3121PyTorch: memory corruption in JIT flatbuffer loader5.50.3%pytorchApr 2MEDICVE-2025-31843OpenAI WP Plugin: broken access control on AI settings4.30.4%—Apr 1MEDIECVE-2025-3001PyTorch: lstm_cell memory corruption, local code exec5.30.2%torchMar 31MEDIECVE-2025-3000PyTorch: memory corruption in torch.jit.script compiler5.30.2%torchMar 31MEDIECVE-2025-2999PyTorch: memory corruption in RNN sequence unpacking5.30.2%torchMar 31MEDIECVE-2025-2998PyTorch: memory corruption in RNN pad_packed_sequence5.30.2%torchMar 31MEDIECVE-2025-2953PyTorch: DoS via mkldnn_max_pool2d resource leak5.50.3%pytorchMar 30MEDIECVE-2025-26265openairinterface5g: segfault enables DoS via crafted UE message6.50.5%openairinterface5gMar 27MEDIECVE-2025-0508SageMaker SDK: MD5 collision silently replaces ML workflows5.90.3%sagemakerMar 20MEDIECVE-2024-7046Open WebUI: missing authz leaks admin credentials4.30.4%open-webuiMar 20MEDIECVE-2024-7045open-webui: missing authz exposes admin prompts4.30.4%open-webuiMar 20MEDIECVE-2024-7035Open WebUI: CSRF wipes RAG DB and AI memories via GET6.98.7%open-webuiMar 20MEDIECVE-2024-7034open-webui: path traversal allows arbitrary file write/RCE6.52.5%open-webuiMar 20MEDIECVE-2024-7033open-webui: path traversal allows file write and RCE6.51.1%open-webuiMar 20MEDIECVE-2024-7044Open WebUI: Stored XSS via file upload, session hijack6.80.5%open-webuiMar 20Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
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