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
3,591

AI/ML CVEs Tracked

481

Critical

96

New This Week

24

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 3591 results
HIGH EXPLOIT AVAIL

TensorFlow: DoS via malformed numpy array shape

CVE-2022-41884
7.5
EPSS 0.4%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
CRITICAL EXPLOIT AVAIL

TensorFlow: heap OOB read in candidate sampler op

CVE-2022-41880
9.1
EPSS 0.4%
Data Extraction DoS Code Execution Framework Inference Training Data
tensorflow 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: executor crash via malformed op inputs (DoS)

CVE-2022-41883
7.5
EPSS 0.4%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

Label Studio: SSRF + file read, self-reg bypass

CVE-2022-36551
6.5
EPSS 5.6%
Data Extraction Auth Bypass Data Leakage Training Data Framework
label-studio Patch: 1.6.0 CWE-918 2 6 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS crash in transposed conv quantization

CVE-2022-36027
7.5
EPSS 0.8%
DoS Framework
tensorflow 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS via malformed Requantize tensors

CVE-2022-36017
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: CHECK-fail assertion crashes model serving

CVE-2022-36016
7.5
EPSS 0.7%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: integer overflow in RangeSize causes DoS

CVE-2022-36015
7.5
EPSS 0.7%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: null ptr dereference in MLIR causes remote DoS

CVE-2022-36014
7.5
EPSS 0.7%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow MLIR: null ptr deref crashes model serving

CVE-2022-36013
7.5
EPSS 0.7%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: DoS via empty MLIR function attributes

CVE-2022-36012
7.5
EPSS 0.7%
DoS Framework Inference
tensorflow CWE-617 3.8K 3 ATLAS
HIGH

TensorFlow: null deref DoS in MLIR function conversion

CVE-2022-36011
7.5
EPSS 0.5%
DoS Supply Chain Framework Inference
tensorflow 3.8K 4 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS via CHECK fail in fake_quant gradient

CVE-2022-36005
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS via tf.random.gamma CHECK assertion

CVE-2022-36004
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: DoS via RandomPoissonV2 large input

CVE-2022-36003
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: DoS via Unbatch assertion failure

CVE-2022-36002
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: DoS via type confusion in DrawBoundingBoxes

CVE-2022-36001
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH

TensorFlow: null deref crashes MLIR graph conversion

CVE-2022-36000
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow CWE-476 3.8K 3 ATLAS
HIGH

TensorFlow: DoS via empty Conv2DBackpropInput tensors

CVE-2022-35999
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS via EmptyTensorList CHECK fail

CVE-2022-35998
7.5
EPSS 0.5%
DoS Framework Inference
tensorflow 3.8K 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