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 1908 results — High severity
HIGH

TensorFlow: integer overflow in EditDistance causes DoS

CVE-2023-25662
7.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGH

TensorFlow: null ptr deref in Print op allows remote DoS

CVE-2023-25660
7.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGH

TensorFlow: OOB read in DynamicStitch enables DoS

CVE-2023-25659
7.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGH

TensorFlow: OOB read in GRUBlockCellGrad causes DoS

CVE-2023-25658
7.5
EPSS 0.4%
DoSCode ExecutionFrameworkInferenceTraining Data
tensorflow3.4K4 ATLAS
HIGH

Grafana GeoMap: stored XSS enables Editor-to-Admin escalation

CVE-2023-0507
7.3
EPSS 15.5%
Auth BypassData LeakageFrameworkPlugin
2 ATLAS
HIGH

Grafana: stored XSS in GeoMap SVG enables admin takeover

CVE-2022-23552
7.3
EPSS 0.8%
Auth BypassData LeakageFramework
2 ATLAS
HIGH

TensorFlow: type confusion DoS via bool cast in tensors

CVE-2022-41911
7.5
EPSS 0.4%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: remote DoS via malformed tensor input

CVE-2022-41909
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-4763.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via invalid UTF-8 input to PyFunc op

CVE-2022-41908
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: integer overflow in ResizeNearestNeighborGrad → DoS

CVE-2022-41907
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via SparseMatrixNNZ CHECK assertion fail

CVE-2022-41901
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: SdcaOptimizer DoS via malformed tensor rank

CVE-2022-41899
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS crash via empty SparseFillEmptyRowsGrad inputs

CVE-2022-41898
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: OOB read in FractionMaxPoolGrad causes DoS

CVE-2022-41897
7.5
EPSS 0.5%
DoSFrameworkInferenceTraining Data
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via oversized filterbank_channel_count

CVE-2022-41896
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-12843.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB in MirrorPadGrad causes DoS

CVE-2022-41895
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow Lite: buffer overflow in CONV_3D_TRANSPOSE op

CVE-2022-41894
8.1
EPSS 0.6%
Code ExecutionSupply ChainFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via TensorListResize malformed input

CVE-2022-41893
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: segfault DoS in TensorListConcat op

CVE-2022-41891
7.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: int32 overflow in BCast::ToShape causes DoS

CVE-2022-41890
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