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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1295 results — High severity, no patch
HIGH

TensorFlow: heap OOB read in sparse reduction ops

CVE-2021-37635
7.1
EPSS 0.2%
Data ExtractionDoSFrameworkTraining Data
tensorflowCWE-1253.4K3 ATLAS
HIGH

TensorFlow: null deref in MatrixDiagPartOp, DoS risk

CVE-2021-37643
7.1
EPSS 0.2%
DoSCode ExecutionFrameworkTraining Data
tensorflow3.4K3 ATLAS
HIGH

TensorFlow: heap OOB read via tensor restore API

CVE-2021-37639
7.8
EPSS 0.2%
Code ExecutionData ExtractionFrameworkTraining Data
tensorflowCWE-1253.4K3 ATLAS
HIGH

TensorFlow: null ptr deref in RaggedTensorToTensor op

CVE-2021-37638
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: null ptr deref in graph optimizer

CVE-2021-29616
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkInference
tensorflowCWE-4763.4K2 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: OOB write in decode_raw crashes interpreter

CVE-2021-29614
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkTraining Data
tensorflowCWE-7873.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: CTCLoss heap OOB read, info leak + crash

CVE-2021-29613
7.1
EPSS 0.2%
DoSData ExtractionFrameworkInference
tensorflowCWE-1253.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap overflow in linalg op, RCE risk

CVE-2021-29612
7.8
EPSS 0.3%
Code ExecutionFrameworkInference
tensorflowCWE-7873.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap R/W via quantization axis underflow

CVE-2021-29610
7.8
EPSS 0.2%
Code ExecutionData ExtractionFrameworkInference
tensorflowCWE-7873.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: SparseAdd heap OOB write and null deref

CVE-2021-29609
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkInference
tensorflowCWE-4763.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB in RaggedTensorToTensor op

CVE-2021-29608
7.8
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB write in SparseAdd op

CVE-2021-29607
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkInferenceTraining Data
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow Lite: OOB read via crafted TFLite model

CVE-2021-29606
7.8
EPSS 0.2%
Supply ChainCode ExecutionData ExtractionFrameworkInference
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow TFLite: heap OOB write via malformed model

CVE-2021-29603
7.8
EPSS 0.2%
Code ExecutionSupply ChainFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow Lite: integer overflow in model concatenation

CVE-2021-29601
7.1
EPSS 0.2%
Supply ChainCode ExecutionFrameworkModelInference
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow TFLite: div-by-zero via crafted OneHot model

CVE-2021-29600
7.8
EPSS 0.2%
DoSCode ExecutionSupply ChainFrameworkInferenceModel
tensorflowCWE-3693.4K3 ATLAS
HIGHEXPLOIT AVAIL

TFLite Split: malicious model triggers div-by-zero (DoS/RCE)

CVE-2021-29599
7.8
EPSS 0.2%
DoSCode ExecutionSupply ChainFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow TFLite: SVDF div-by-zero enables RCE

CVE-2021-29598
7.8
EPSS 0.2%
Code ExecutionDoSSupply ChainFrameworkInferenceModel
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow TFLite: div-by-zero crash via crafted model

CVE-2021-29597
7.8
EPSS 0.2%
DoSCode ExecutionSupply ChainFrameworkInference
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow TFLite: div-by-zero in EmbeddingLookup op

CVE-2021-29596
7.8
EPSS 0.2%
DoSCode ExecutionSupply ChainFrameworkInferenceModel
tensorflow3.4K3 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