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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
2,409

AI/ML CVEs Tracked

347

Critical

298

New This Week

18

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 850 results — Medium severity
Severity CVE ID Summary CVSS EPSS Package Date
MEDI E CVE-2024-1455 LangChain: Billion Laughs XML expansion causes DoS 5.9 0.8% langchain Mar 26 MEDI CVE-2023-30767 Intel TF Opt: buffer overflow enables local privesc 6.7 0.2% optimization_for_tensorflow Feb 14 MEDI E CVE-2023-6568 MLflow: reflected XSS via Content-Type header injection 6.1 1.6% mlflow Dec 7 MEDI CVE-2023-48299 TorchServe: ZipSlip arbitrary file write via model upload 5.3 0.7% torchserve Nov 21 MEDI CVE-2023-41626 Gradio: arbitrary file upload via /upload endpoint 4.8 0.3% gradio Sep 15 MEDI E CVE-2023-34094 ChuanhuChatGPT: config exposure leaks API keys 5.3 0.6% chuanhuchatgpt Jun 2 MEDI E CVE-2023-2800 Transformers: temp file race condition allows local DoS 4.7 0.3% transformers May 18 MEDI E CVE-2023-27562 n8n: path traversal allows arbitrary file read 6.5 2.3% n8n May 10 MEDI E CVE-2023-1651 AI ChatBot WP: auth bypass exposes OpenAI config + XSS 5.4 0.2% wpbot May 8 MEDI E CVE-2023-25661 TensorFlow: DoS via malformed Convolution3D input 6.5 0.4% tensorflow Mar 27 MEDI CVE-2023-27494 Streamlit: reflected XSS enables session hijacking 6.1 0.4% streamlit Mar 16 MEDI E CVE-2022-36551 Label Studio: SSRF + file read, self-reg bypass 6.5 5.1% label-studio Oct 4 MEDI CVE-2022-35918 Streamlit: path traversal leaks server filesystem 6.5 1.3% streamlit Aug 1 MEDI E CVE-2022-29213 TensorFlow: input validation DoS in FFT signal ops 5.5 0.3% tensorflow May 21 MEDI E CVE-2022-29212 TensorFlow Lite: quantization assert crash (DoS) 5.5 0.3% tensorflow May 21 MEDI E CVE-2022-29211 TensorFlow: NaN input crashes histogram op (CPU DoS) 5.5 0.3% tensorflow May 21 MEDI CVE-2022-29210 TensorFlow: heap OOB in TensorKey causes DoS 5.5 0.2% tensorflow May 21 MEDI E CVE-2022-29209 TensorFlow: CHECK macro type confusion causes DoS 5.5 0.4% tensorflow May 21 MEDI E CVE-2022-29206 TensorFlow: SparseTensorDenseAdd null ptr deref DoS 5.5 0.3% tensorflow May 20 MEDI E CVE-2022-29205 TensorFlow: NULL deref DoS via compat.v1 ops 5.5 0.3% tensorflow May 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