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:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4307 results
HIGHEXPLOIT AVAIL

TensorFlow: remote DoS via BlockLSTMGradV2 validation

CVE-2022-35964
7.5
EPSS 0.5%
DoSFrameworkTraining DataInference
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via FractionalAvgPoolGrad overflow

CVE-2022-35963
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via malformed TensorListReserve input

CVE-2022-35960
7.5
EPSS 0.7%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via AvgPool3DGradOp input overflow

CVE-2022-35959
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via UnbatchGradOp assertion crash

CVE-2022-35952
7.5
EPSS 0.7%
DoSFrameworkInference
tensorflowCWE-6173.4K2 ATLAS
HIGH

TensorFlow: DoS via negative ksize in AvgPoolOp

CVE-2022-35941
7.5
EPSS 0.7%
DoSFrameworkInference
tensorflow3.4K2 ATLAS
HIGH

TensorFlow: integer overflow in RaggedRangeOp crashes service

CVE-2022-35940
7.5
EPSS 0.7%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
CRITICAL

TensorFlow: ScatterNd OOB write enables RCE/crash

CVE-2022-35939
9.8
EPSS 0.6%
Code ExecutionDoSFrameworkInference
tensorflow3.4K4 ATLAS
CRITICAL

TensorFlow: OOB read in GatherNd causes crash/data leak

CVE-2022-35938
9.1
EPSS 0.6%
DoSData ExtractionCode ExecutionFrameworkInference
tensorflow3.4K4 ATLAS
CRITICAL

TensorFlow: GatherNd OOB read crashes inference servers

CVE-2022-35937
9.1
EPSS 0.6%
DoSData ExtractionSupply ChainFrameworkInference
tensorflow3.4K5 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via SobolSample CHECK-failure

CVE-2022-35935
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: tf.reshape DoS via integer overflow

CVE-2022-35934
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUM

Streamlit: path traversal leaks server filesystem

CVE-2022-35918
6.5
EPSS 1.8%
Data ExtractionData LeakageFramework
streamlitCWE-223.1K5 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow CLI: eval() injection enables reverse shell

CVE-2022-29216
7.8
EPSS 0.5%
Code ExecutionSupply ChainFrameworkInference
tensorflow3.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: input validation DoS in FFT signal ops

CVE-2022-29213
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow Lite: quantization assert crash (DoS)

CVE-2022-29212
5.5
EPSS 0.3%
DoSSupply ChainFrameworkInferenceModel
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: NaN input crashes histogram op (CPU DoS)

CVE-2022-29211
5.5
EPSS 0.3%
DoSFrameworkTraining Data
tensorflow3.4K4 ATLAS
MEDIUM

TensorFlow: heap OOB in TensorKey causes DoS

CVE-2022-29210
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflowCWE-7873.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: CHECK macro type confusion causes DoS

CVE-2022-29209
5.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: OOB write in EditDistance enables local DoS

CVE-2022-29208
7.1
EPSS 0.4%
DoSCode ExecutionFramework
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