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
2,374

AI/ML CVEs Tracked

344

Critical

407

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 16 of 536 results — Medium severity, no patch
MEDIUM EXPLOIT AVAIL

TensorFlow Lite: OOM DoS via crafted segment sum model

CVE-2020-15213
4.0
EPSS 0.6%
DoS Framework Inference Model
tensorflow CWE-770 3.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow Lite: heap OOB RW via flatbuffer tensor index

CVE-2020-15211
4.8
EPSS 0.9%
Code Execution Supply Chain Data Extraction Framework Inference Model
tensorflow 3.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow Lite: memory corruption via aliased tensors

CVE-2020-15210
6.5
EPSS 0.7%
Supply Chain DoS Code Execution Framework Inference Model
tensorflow CWE-787 3.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow Lite: null ptr deref crashes model inference

CVE-2020-15209
5.9
EPSS 0.8%
DoS Supply Chain Framework Inference Model
tensorflow 3.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr deref DoS in eager mode ops

CVE-2020-15204
5.3
EPSS 0.9%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: heap overflow in ragged tensor ops

CVE-2020-15201
4.8
EPSS 0.6%
Code Execution Data Extraction Framework Inference
tensorflow CWE-787 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: heap overflow in RaggedCountSparseOutput DoS

CVE-2020-15200
5.9
EPSS 0.8%
DoS Code Execution Framework Inference
tensorflow CWE-787 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via malformed ragged tensor input

CVE-2020-15199
5.9
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-20 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: heap OOB in SparseCountSparseOutput ops

CVE-2020-15198
5.4
EPSS 0.5%
Code Execution DoS Framework Inference
tensorflow CWE-119 3.7K 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via malformed sparse tensor input

CVE-2020-15197
6.3
EPSS 0.7%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via SparseFillEmptyRowsGrad assertion

CVE-2020-15194
5.3
EPSS 1.0%
DoS Framework Inference
tensorflow CWE-617 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: memory leak in dlpack DoS via low-priv input

CVE-2020-15192
4.3
EPSS 0.7%
DoS Framework Inference
tensorflow CWE-20 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr deref in dlpack causes remote DoS

CVE-2020-15191
5.3
EPSS 0.7%
DoS Code Execution Framework Inference
tensorflow CWE-252 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr deref DoS via Switch op eager runtime

CVE-2020-15190
5.3
EPSS 0.9%
DoS Framework Inference
tensorflow CWE-476 3.7K 3 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
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

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