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.

Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,018

AI/ML CVEs Tracked

424

Critical

114

New This Week

19

In CISA KEV

Latest AI Security Threats

Showing 18 of 3018 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2020-15193 TensorFlow: uninitialized memory corruption via dlpack 7.1 0.8% tensorflow Sep 25 MEDI E CVE-2020-15192 TensorFlow: memory leak in dlpack DoS via low-priv input 4.3 0.8% tensorflow Sep 25 MEDI E CVE-2020-15191 TensorFlow: null ptr deref in dlpack causes remote DoS 5.3 0.9% tensorflow Sep 25 MEDI E CVE-2020-15190 TensorFlow: null ptr deref DoS via Switch op eager runtime 5.3 0.9% tensorflow Sep 25 UNKN CVE-2020-25514 Sourcecodester LMS: broken access control in admin panel 0.6% Sep 22 CRIT E CVE-2020-13092 scikit-learn: RCE via malicious joblib model deserialization 9.8 2.7% scikit-learn May 15 MEDI CVE-2018-21233 TensorFlow: integer overflow leaks process memory via BMP 6.5 0.6% tensorflow May 4 HIGH E CVE-2020-5215 TensorFlow: type confusion DoS crashes eager mode inference 7.5 0.6% tensorflow Jan 28 CRIT CVE-2019-16778 TensorFlow: heap overflow in UnsortedSegmentSum op 9.8 0.8% tensorflow Dec 16 MEDI CVE-2018-21030 Jupyter Notebook: XSS via missing CSP on served files 5.3 1.4% notebook Nov 8 MEDI CVE-2019-6576 SIMATIC WinCC: TLS key disclosure enables traffic decryption 6.5 1.7% SIMATIC HMI Classic Devices (TP/MP/OP/MP Mobile Panel) May 14 UNKN CVE-2018-7575 TensorFlow: buffer overflow, potential RCE in 1.7.x 0.6% tensorflow Apr 24 UNKN E CVE-2019-9635 TensorFlow: NULL ptr deref DoS via malformed GIF input 0.5% tensorflow Apr 24 UNKN CVE-2018-7577 TensorFlow: Snappy memcpy overlap crash/mem disclosure 0.5% tensorflow Apr 24 UNKN E CVE-2018-10055 TensorFlow XLA: heap overflow via crafted config file 0.5% tensorflow Apr 24 HIGH CVE-2018-8825 TensorFlow 1.7: Buffer overflow enables arbitrary code exec 8.8 0.7% tensorflow Apr 23 UNKN CVE-2018-7576 TensorFlow: NPD in 1.6.x crashes ML runtime 0.5% tensorflow Apr 23 HIGH CVE-2018-8768 Jupyter Notebook: XSS via malicious .ipynb file 7.8 1.1% notebook Jul 12

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