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 2390 results GHSA-564p-rx2q-4c8v BentoML: open redirect exposes ML teams to phishing 6.1 — bentoml Mar 20 HIGH E CVE-2024-12537 Open-WebUI: unauthenticated DoS via code formatter 7.5 0.9% open-webui Mar 20 CRIT E CVE-2024-11958 llama-index DuckDB retriever: SQLi enables RCE 9.8 1.3% llama-index-retrievers-duckdb-retriever Mar 20 HIGH E CVE-2024-10572 H2O-3: unauthenticated AST parser enables DoS + file write 7.5 0.6% h2o Mar 20 MEDI E CVE-2025-1474 MLflow: passwordless accounts enable persistent backdoor 5.5 0.3% mlflow Mar 20 HIGH E CVE-2025-1473 MLflow: CSRF in signup allows rogue account creation 7.1 0.2% mlflow Mar 20 HIGH E CVE-2025-0453 MLflow: GraphQL DoS disables ML tracking server 7.5 0.5% mlflow Mar 20 HIGH E CVE-2025-0317 Ollama: DoS via malicious GGUF model file upload 7.5 13.5% ollama Mar 20 HIGH E CVE-2025-0315 Ollama: GGUF model upload causes memory exhaustion DoS 7.5 0.7% ollama Mar 20 HIGH E CVE-2025-0312 Ollama: null pointer DoS via malicious GGUF model upload 7.5 0.6% ollama Mar 20 UNKN E CVE-2025-0187 Gradio: DoS via oversized upload filename — 0.7% gradio Mar 20 CRIT E CVE-2024-9070 BentoML: unauthenticated RCE via runner deserialization 9.8 0.8% bentoml Mar 20 HIGH E CVE-2024-9056 BentoML: DoS via multipart boundary exhausts server 7.5 0.7% bentoml Mar 20 CRIT E CVE-2024-9053 vllm: RCE via unsafe pickle deserialization in RPC server 9.8 1.3% vllm Mar 20 HIGH E CVE-2024-8966 Gradio: DoS via malformed multipart boundary 7.5 0.7% video Mar 20 HIGH E CVE-2024-8859 MLflow: path traversal allows arbitrary file read via DBFS 7.5 2.5% mlflow Mar 20 HIGH E CVE-2024-8063 ollama: divide-by-zero DoS via crafted GGUF model import 7.5 0.6% ollama Mar 20 MEDI E CVE-2024-8021 Gradio: open redirect exposes AI demo users to phishing 6.1 0.7% gradio Mar 20 HIGH E CVE-2024-7959 Open-WebUI: SSRF via unchecked OpenAI URL leaks internal secrets 7.7 24.5% open-webui Mar 20 MEDI E CVE-2024-6838 MLflow: unconstrained input causes UI denial of service 5.3 0.6% mlflow Mar 20 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