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 565 results — Medium severity, Active exploitation
MEDIUMEXPLOIT AVAIL

TensorFlow: null-ptr deref in eager mode causes DoS

CVE-2022-29207
5.5
EPSS 0.3%
DoSFrameworkTraining DataInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: LSTMBlockCell DoS via invalid tensor rank

CVE-2022-29200
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflowCWE-12843.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: CHECK-fail DoS in LoadAndRemapMatrix op

CVE-2022-29199
5.5
EPSS 0.3%
DoSFramework
tensorflow3.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via sparse tensor input validation failure

CVE-2022-29198
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via UnsortedSegmentJoin input validation

CVE-2022-29197
5.5
EPSS 0.3%
DoSFramework
tensorflowCWE-203.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via invalid Conv3D filter input

CVE-2022-29196
5.5
EPSS 0.3%
DoSFramework
tensorflowCWE-12843.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: StagePeek DoS via unvalidated index scalar

CVE-2022-29195
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via TensorSummaryV2 input validation failure

CVE-2022-29193
5.5
EPSS 0.3%
DoSFrameworkTraining Data
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via malformed DeleteSessionTensor input

CVE-2022-29194
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflow3.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via QuantizeAndDequantize input validation

CVE-2022-29192
5.5
EPSS 0.3%
DoSFramework
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via GetSessionTensor input validation

CVE-2022-29191
5.5
EPSS 0.4%
DoSFramework
tensorflow3.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow XLA: null pointer dereference causes DoS

CVE-2022-23595
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow Grappler: DoS via malicious SavedModel

CVE-2022-23589
6.5
EPSS 1.1%
DoSSupply ChainFrameworkModel
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via crafted SavedModel crashes Grappler

CVE-2022-23588
6.5
EPSS 0.9%
DoSSupply ChainFrameworkModelInference
tensorflow3.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: SavedModel DoS crashes Python interpreter

CVE-2022-23586
6.5
EPSS 0.8%
DoSFrameworkModel
tensorflow3.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: memory leak in PNG decode causes DoS

CVE-2022-23585
6.5
EPSS 1.0%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: use-after-free in PNG decode causes DoS

CVE-2022-23584
6.5
EPSS 0.7%
DoSCode ExecutionFrameworkInference
tensorflow3.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: SavedModel type confusion triggers DoS crash

CVE-2022-23583
6.5
EPSS 0.9%
DoSSupply ChainFrameworkModelInference
tensorflowCWE-8433.4K5 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: SavedModel CHECK-fail causes DoS

CVE-2022-23582
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via Grappler optimizer CHECK failure

CVE-2022-23581
6.5
EPSS 1.2%
DoSSupply ChainFrameworkModelInference
tensorflow3.4K4 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