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
2,173

AI/ML CVEs Tracked

330

Critical

251

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 13 of 2173 results
CRITICAL EXPLOIT AVAIL

scikit-learn: RCE via malicious joblib model deserialization

CVE-2020-13092
9.8
EPSS 2.6%
Code Execution Supply Chain Framework Model
scikit-learn CWE-502 29.2K 5 ATLAS
MEDIUM

TensorFlow: integer overflow leaks process memory via BMP

CVE-2018-21233
6.5
EPSS 0.5%
Data Extraction Privacy Violation Supply Chain Framework Inference
tensorflow CWE-125 3.7K 4 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: type confusion DoS crashes eager mode inference

CVE-2020-5215
7.5
EPSS 0.6%
DoS Supply Chain Framework Inference
tensorflow CWE-20 3.7K 5 ATLAS
CRITICAL

TensorFlow: heap overflow in UnsortedSegmentSum op

CVE-2019-16778
9.8
EPSS 0.8%
Code Execution Supply Chain Framework Inference
tensorflow CWE-681 3.7K 3 ATLAS
MEDIUM

Jupyter Notebook: XSS via missing CSP on served files

CVE-2018-21030
5.3
EPSS 1.4%
Code Execution Data Leakage Framework
notebook Patch: 5.5.0rc1 CWE-79 3.0K 3 ATLAS
MEDIUM

SIMATIC WinCC: TLS key disclosure enables traffic decryption

CVE-2019-6576
6.5
EPSS 1.7%
Data Leakage Privacy Violation Inference Framework
SIMATIC HMI Classic Devices (TP/MP/OP/MP Mobile Panel) 479 3 ATLAS
UNKNOWN

TensorFlow: buffer overflow, potential RCE in 1.7.x

CVE-2018-7575
--
EPSS 0.5%
Code Execution Supply Chain Framework Model
tensorflow CWE-190 3.7K 4 ATLAS
UNKNOWN EXPLOIT AVAIL

TensorFlow: NULL ptr deref DoS via malformed GIF input

CVE-2019-9635
--
EPSS 0.5%
DoS Framework Inference
tensorflow CWE-476 3.7K 3 ATLAS
UNKNOWN

TensorFlow: Snappy memcpy overlap crash/mem disclosure

CVE-2018-7577
--
EPSS 0.4%
DoS Data Extraction Supply Chain Framework Training Data Inference
tensorflow CWE-20 3.7K 3 ATLAS
UNKNOWN EXPLOIT AVAIL

TensorFlow XLA: heap overflow via crafted config file

CVE-2018-10055
--
EPSS 0.4%
Code Execution DoS Framework Training Data
tensorflow CWE-119 3.7K 3 ATLAS
HIGH

TensorFlow 1.7: Buffer overflow enables arbitrary code exec

CVE-2018-8825
8.8
EPSS 0.6%
Code Execution Supply Chain Framework Inference Model
tensorflow CWE-119 3.7K 5 ATLAS
UNKNOWN

TensorFlow: NPD in 1.6.x crashes ML runtime

CVE-2018-7576
--
EPSS 0.4%
DoS Code Execution Framework Inference
tensorflow CWE-476 3.7K 3 ATLAS
HIGH

Jupyter Notebook: XSS via malicious .ipynb file

CVE-2018-8768
7.8
EPSS 1.1%
Code Execution Supply Chain Data Extraction Framework
notebook Patch: 5.4.1 3.0K 5 ATLAS

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