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 patchNVIDIA: Deserialization enables RCE
CVE-2025-33213 n8n: security flaw enables exploitation
CVE-2025-65964 langflow: security flaw enables exploitation
CVE-2025-34291 mcp-server-kubernetes: Command Injection enables RCE
CVE-2025-66404 vllm: Code Injection enables RCE
CVE-2025-66448 mlx: security flaw enables exploitation
CVE-2025-62609 AI component: Arbitrary File Upload enables RCE
CVE-2025-12973 vllm: Input Validation flaw enables exploitation
CVE-2025-62164 n8n: security flaw enables exploitation
CVE-2025-62726 vLLM: timing attack enables API key bypass
CVE-2025-59425 Flowise: unrestricted file upload enables persistent RCE
CVE-2025-61687 PyTorch: DoS via sparse/dense tensor Inductor compile
CVE-2025-55560 TensorFlow: DoS via Conv2D valid padding crash
CVE-2025-55559 PyTorch: Inductor compiler buffer overflow causes DoS
CVE-2025-55558 PyTorch: DoS via cummin+Inductor NameError in 2.7.0
CVE-2025-55557 PyTorch 2.7.0: DoS via proxy_tensor.py syntax error
CVE-2025-55553 PyTorch: integer overflow in rot90+randn_like causes DoS
CVE-2025-55552 PyTorch: DoS in linalg.lu via malformed slice op
CVE-2025-55551 Transformers: ReDoS in optimizer halts training pipelines
CVE-2025-6921 Flowise: unauthenticated SSRF exposes internal network
CVE-2025-59527 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