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 1961 results — Active exploitationCVE-2023-2356MLflow: path traversal allows unauthenticated file read7.54.2%mlflowApr 28CRITECVE-2023-29374LangChain: RCE via prompt injection in LLMMathChain9.839.7%langchainApr 5MEDIECVE-2023-25661TensorFlow: DoS via malformed Convolution3D input6.50.4%tensorflowMar 27HIGHECVE-2023-25801TensorFlow: double-free in pooling ops enables RCE7.80.1%tensorflowMar 25HIGHECVE-2023-25674TensorFlow: null pointer DoS in RandomShuffle (XLA)7.50.4%tensorflowMar 25CRITECVE-2023-25668TensorFlow: unauthenticated RCE via heap buffer overflow9.80.8%tensorflowMar 25HIGHECVE-2023-25667TensorFlow: integer overflow DoS in video frame decoding7.50.3%tensorflowMar 25HIGHECVE-2023-25665TensorFlow: null ptr deref DoS via sparse tensors7.50.4%tensorflowMar 25CRITECVE-2023-25664TensorFlow: heap overflow in AvgPoolGrad, RCE risk9.80.4%tensorflowMar 25CRITCVE-2023-1177MLflow: path traversal allows arbitrary file read/write9.869.7%mlflowMar 24LOWECVE-2023-1176MLflow: path traversal exposes arbitrary local files3.30.6%mlflowMar 24CRITECVE-2023-25823Gradio: hardcoded SSH key leaks via share=True demos9.80.6%gradioFeb 23CRITECVE-2022-41902TensorFlow Grappler: OOB read/crash via crafted model9.10.5%tensorflowDec 6CRITECVE-2022-45907PyTorch: RCE via unsafe eval in JIT annotations9.81.3%pytorchNov 26CRITECVE-2022-44194Netgear R7000P: buffer overflow via DNS params9.81.5%—Nov 22HIGHECVE-2022-41909TensorFlow: remote DoS via malformed tensor input7.50.5%tensorflowNov 18HIGHECVE-2022-41908TensorFlow: DoS via invalid UTF-8 input to PyFunc op7.50.5%tensorflowNov 18HIGHECVE-2022-41907TensorFlow: integer overflow in ResizeNearestNeighborGrad → DoS7.50.5%tensorflowNov 18HIGHECVE-2022-41901TensorFlow: DoS via SparseMatrixNNZ CHECK assertion fail7.50.5%tensorflowNov 18CRITECVE-2022-41900TensorFlow: heap OOB RCE in FractionalMaxPool op9.80.7%tensorflowNov 18Frequently 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