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 910 results — Active exploitationPyTorch: DoS via cummin+Inductor NameError in 2.7.0
CVE-2025-55557 TensorFlow: non-deterministic compilation breaks Embedding
CVE-2025-55556 PyTorch: integer overflow in nan_to_num causes DoS
CVE-2025-55554 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 OpenAI Codex CLI: sandbox escape via model-generated cwd
CVE-2025-59532 Flowise: Unauthenticated RCE via MCP config injection
CVE-2025-59528 Flowise: unauthenticated SSRF exposes internal network
CVE-2025-59527 Flowise Cloud: cross-tenant env var exposure leaks API keys
CVE-2025-59434 Keras: safe_mode bypass enables RCE via model load
CVE-2025-9906 Keras: safe_mode bypass enables RCE via .h5 model files
CVE-2025-9905 picklescan: file extension bypass allows model RCE
CVE-2025-10155 Transformers: ReDoS in EnglishNormalizer exhausts CPU
CVE-2025-6051 Flowise: auth bypass in reset flow allows full ATO
CVE-2025-58434 langchaingo: Jinja2 SSTI allows host filesystem read
CVE-2025-9556 HuggingFace Transformers: ReDoS in MarianTokenizer
CVE-2025-6638 Picklescan: CRC bypass hides malicious pickle in ZIP
CVE-2025-10156 PickleScan: subclass bypass enables malicious model RCE
CVE-2025-10157 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