AI Threat Alert
AI 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 337 results — Critical severity CVE-2024-3573 MLflow: LFI via URI parsing allows arbitrary file read 9.3 0.7% mlflow Apr 16 CRIT E CVE-2024-2912 BentoML: RCE via insecure deserialization (CVSS 10) 10.0 1.5% — Apr 16 CRIT E CVE-2024-3568 HuggingFace Transformers: RCE via pickle deserialization 9.6 2.1% transformers Apr 10 CRIT E CVE-2024-31224 gpt_academic: deserialization RCE, no auth required 9.8 1.2% gpt_academic Apr 8 CRIT E CVE-2024-2057 LangChain TFIDFRetriever: SSRF/RCE via load_local 9.8 0.6% langchain Mar 1 CRIT E CVE-2024-27444 LangChain Experimental: RCE via Python sandbox escape 9.8 0.8% langchain-experimental Feb 26 CRIT E CVE-2024-27133 MLflow: XSS in recipe runner enables Jupyter RCE 9.6 0.7% mlflow Feb 23 CRIT E CVE-2024-27132 MLflow: XSS in recipes enables client-side RCE 9.6 0.9% mlflow Feb 23 CRIT E CVE-2024-0964 Gradio: unauthenticated LFI exposes full server filesystem 9.4 0.9% gradio Feb 5 CRIT E CVE-2024-23751 LlamaIndex: SQL injection in Text-to-SQL feature 9.8 0.7% llamaindex Jan 22 CRIT CVE-2023-48022 Ray: unauthenticated RCE via job submission API 9.8 81.5% ray Nov 28 CRIT E CVE-2023-6020 Ray: unauthenticated LFI exposes entire filesystem 9.3 14.7% ray Nov 16 CRIT E CVE-2023-6014 MLflow: auth bypass allows arbitrary account creation 9.8 1.2% mlflow Nov 16 CRIT E CVE-2023-6021 Ray: LFI allows unauthenticated file read 9.3 37.1% ray Nov 16 CRIT E CVE-2023-6019 Ray: unauthenticated RCE via dashboard command injection 9.8 74.6% ray Nov 16 CRIT E CVE-2023-6018 MLflow: unauth file overwrite enables model poisoning 9.8 47.9% mlflow Nov 16 CRIT E CVE-2023-5245 MLeap: zip slip in model loading enables RCE 9.8 1.2% — Nov 15 CRIT CVE-2023-32785 LangChain: prompt injection → SQL RCE (CVSS 9.8) 9.8 — langchain Oct 21 CRIT CVE-2023-44467 LangChain: RCE bypass via __import__ in PAL chain 9.8 0.9% langchain_experimental Oct 9 CRIT CVE-2023-43654 TorchServe: SSRF + RCE via unrestricted model URL loading 9.8 35.3% torchserve Sep 28 Frequently 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