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

4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 2876 results — no patch

TFLite: infinite loop DoS via crafted strided slice model

CVE-2021-37686

DoSSupply ChainFrameworkInference

tensorflowCWE-8353.4K4 ATLAS

TensorFlow Lite: null ptr deref crashes SVDF inference

CVE-2021-37681

Code ExecutionDoSFrameworkInference

tensorflow3.4K4 ATLAS

TFLite: division by zero crashes fully connected layers

CVE-2021-37680

DoSSupply ChainFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null ptr deref in SparseFillEmptyRows op

CVE-2021-37676

Code ExecutionDoSFrameworkInference

tensorflow3.4K3 ATLAS

MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via division by zero in conv ops

CVE-2021-37675

DoSFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null-ptr deref in Map ops, local C/I/A:High

CVE-2021-37671

DoSCode ExecutionFrameworkTraining DataInference

tensorflow3.4K3 ATLAS

TensorFlow: UnicodeEncode null deref, local code exec

CVE-2021-37667

Code ExecutionDoSFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null-ptr deref in RaggedTensorToVariant op

CVE-2021-37666

Code ExecutionDoSFrameworkTraining Data

tensorflow3.4K3 ATLAS

TensorFlow: double-free in BoostedTrees, code exec

CVE-2021-37652

Code ExecutionFrameworkTraining Data

tensorflowCWE-4153.4K3 ATLAS

TensorFlow SaveV2: null ptr deref, local crash/RCE

CVE-2021-37648

Code ExecutionDoSFrameworkTraining Data

tensorflow3.4K3 ATLAS

TensorFlow: heap OOB read in BoostedTrees ops

CVE-2021-37664

Data ExtractionDoSFrameworkTraining Data

tensorflow3.4K4 ATLAS

TensorFlow: null deref in BoostedTrees training ops

CVE-2021-37662

Code ExecutionDoSFrameworkTraining Data

tensorflow3.4K3 ATLAS

TensorFlow: integer sign conversion DoS in boosted trees

CVE-2021-37661

tensorflowCWE-6813.4K3 ATLAS

TensorFlow: heap OOB in cwise ops enables local RCE

CVE-2021-37659

Code ExecutionDoSFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null ptr deref in MatrixSetDiagV ops

CVE-2021-37658

DoSCode ExecutionFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null ptr deref in MatrixDiagV ops

CVE-2021-37657

Code ExecutionDoSFrameworkInference

tensorflow3.4K3 ATLAS

TensorFlow: null ptr deref in RaggedTensorToSparse op

CVE-2021-37656

Code ExecutionDoSFrameworkTraining DataInference

tensorflow3.4K3 ATLAS

TensorFlow: OOB heap read in ResourceScatterUpdate

CVE-2021-37655

Data ExtractionCode ExecutionFrameworkTraining Data

tensorflow3.4K3 ATLAS

TensorFlow: OOB read/crash via ResourceGather batch_dims

CVE-2021-37654

DoSData ExtractionFrameworkTraining Data

tensorflow3.4K3 ATLAS

TensorFlow: heap OOB r/w in FractionalAvgPoolGrad op

CVE-2021-37651

Code ExecutionDoSFrameworkTraining Data

tensorflowCWE-7873.4K3 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