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 1527 results — Medium severityCVE-2024-36422Flowise: reflected XSS enables session hijack and file read6.10.4%flowiseJul 1MEDIECVE-2024-4940Gradio: open redirect enables phishing against ML users6.11.0%gradioJun 22MEDIECVE-2024-2965langchain-community: DoS via recursive sitemap loop4.20.3%langchainJun 6MEDIECVE-2024-5206scikit-learn: TfidfVectorizer leaks training data tokens4.70.2%scikit-learnJun 6MEDIECVE-2024-3099MLflow: URL encoding bypass enables model poisoning5.40.4%mlflowJun 6MEDIECVE-2024-4858WP Testimonial Carousel: OpenAI API key hijack, no auth5.30.4%—May 25MEDIECVE-2024-0451wpbot: missing auth exposes OpenAI account files5.00.4%wpbotMay 22MEDIECVE-2024-4263MLflow: broken access control allows artifact deletion5.40.3%mlflowMay 16MEDIECVE-2024-1726Quarkus RESTEasy: DoS via late-stage auth checks5.30.7%—Apr 25MEDICVE-2023-5675Quarkus: JAX-RS authorization not enforced on methods6.50.5%—Apr 25MEDICVE-2024-31584PyTorch: OOB read in mobile model loader leaks memory5.50.4%pytorchApr 19MEDIECVE-2024-31580PyTorch: heap buffer overflow causes local DoS4.00.2%pytorchApr 17MEDICVE-2024-31462stable-diffusion-webui: path traversal file write6.30.7%—Apr 12MEDIECVE-2024-28224Ollama: DNS rebinding exposes LLM API to remote access6.60.4%ollamaApr 8MEDIECVE-2024-1023Vert.x: memory leak in HTTP client enables DoS6.51.7%—Mar 27MEDIECVE-2024-2206Gradio: SSRF exposes internal HuggingFace endpoints6.50.4%gradioMar 27MEDIECVE-2024-1455LangChain: Billion Laughs XML expansion causes DoS5.90.8%langchainMar 26MEDICVE-2023-30767Intel TF Opt: buffer overflow enables local privesc6.70.2%optimization_for_tensorflowFeb 14MEDIECVE-2023-6568MLflow: reflected XSS via Content-Type header injection6.11.7%mlflowDec 7MEDICVE-2023-48299TorchServe: ZipSlip arbitrary file write via model upload5.30.7%torchserveNov 21Frequently 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