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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 2377 results
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via empty tensor in FractionalMaxPoolGrad

CVE-2021-29580
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap buffer overflow in MaxPoolGrad kernel

CVE-2021-29579
7.8
EPSS 0.2%
Code Execution Framework Inference
tensorflow CWE-787 3.7K 2 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap buffer overflow in FractionalAvgPoolGrad

CVE-2021-29578
7.8
EPSS 0.2%
Code Execution Framework Training Data
tensorflow CWE-787 3.7K 2 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap overflow in AvgPool3DGrad op

CVE-2021-29577
7.8
EPSS 0.2%
Code Execution Framework Inference
tensorflow CWE-787 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap buffer overflow in MaxPool3DGradGrad op

CVE-2021-29576
7.8
EPSS 0.2%
Code Execution Framework
tensorflow CWE-787 3.7K 2 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: stack overflow DoS in ReverseSequence op

CVE-2021-29575
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow CWE-787 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: null ptr deref in MaxPool3DGradGrad ops

CVE-2021-29574
7.8
EPSS 0.2%
DoS Code Execution Framework Inference
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: div-by-zero in MaxPoolGrad op causes DoS

CVE-2021-29573
5.5
EPSS 0.2%
DoS Framework Training Data
tensorflow CWE-369 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr deref crashes SdcaOptimizer op

CVE-2021-29572
5.5
EPSS 0.2%
DoS Framework Training Data
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap OOB write via crafted bounding box op

CVE-2021-29571
7.8
EPSS 0.2%
Code Execution Supply Chain Framework Inference
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: OOB read in MaxPoolGradWithArgmax op

CVE-2021-29570
7.1
EPSS 0.2%
DoS Data Extraction Framework Inference
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: OOB heap read in MaxPoolGradWithArgmax op

CVE-2021-29569
7.1
EPSS 0.2%
Data Extraction DoS Framework
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: null deref in ParameterizedTruncatedNormal op

CVE-2021-29568
7.8
EPSS 0.2%
Code Execution DoS Framework Inference
tensorflow CWE-476 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via SparseDenseCwiseMul OOB

CVE-2021-29567
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap OOB write in Dilation2D training op

CVE-2021-29566
7.8
EPSS 0.2%
Code Execution Supply Chain Framework Training Data
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr dereference crashes sparse ops

CVE-2021-29565
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: null ptr deref DoS in EditDistance op

CVE-2021-29564
5.5
EPSS 0.2%
DoS Framework
tensorflow 3.7K 2 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via RFFT empty matrix assertion crash

CVE-2021-29563
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: assertion failure DoS in IRFFT op

CVE-2021-29562
5.5
EPSS 0.2%
DoS Framework
tensorflow 3.7K 2 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via malformed LoadAndRemapMatrix input

CVE-2021-29561
5.5
EPSS 0.2%
DoS Framework Inference
tensorflow 3.7K 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