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 1346 results — Active exploitation, no patch
HIGHEXPLOIT AVAIL

TensorFlow: DoS via Save/SaveSlices dtype CHECK fail

CVE-2022-35983
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via invalid SparseBincount input

CVE-2022-35982
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via FractionalMaxPoolGrad assertion

CVE-2022-35981
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via nonscalar input in QuantizedRelu

CVE-2022-35979
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via nonscalar quantization op input

CVE-2022-35974
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via QuantizedMatMul input validation

CVE-2022-35973
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via QuantizedBiasAdd rank validation

CVE-2022-35972
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via invalid quantization tensor rank

CVE-2022-35971
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via malformed QuantizedInstanceNorm tensors

CVE-2022-35970
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via malformed Conv2DBackpropInput

CVE-2022-35969
7.5
EPSS 0.5%
DoSFrameworkAPI
tensorflowCWE-6173.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via AvgPoolGrad shape validation failure

CVE-2022-35968
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via QuantizedAdd tensor rank flaw

CVE-2022-35967
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via QuantizedAvgPool input validation

CVE-2022-35966
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: NULL deref DoS via empty tensor input

CVE-2022-35965
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
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
HIGHEXPLOIT AVAIL

TensorFlow: DoS via SobolSample CHECK-failure

CVE-2022-35935
7.5
EPSS 0.5%
DoSFrameworkInference
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