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
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
HIGHEXPLOIT AVAIL

Gradio: CSV formula injection via flagging enables RCE

CVE-2022-24770
8.8
EPSS 1.3%
Code ExecutionSupply ChainFrameworkInference
gradio7354 ATLAS
CRITICALEXPLOIT AVAIL

pytorch-lightning: code injection enables full RCE

CVE-2022-0845
9.8
EPSS 1.0%
Code ExecutionSupply ChainFrameworkTraining Data
pytorch_lightningCWE-9426.1K3 ATLAS
UNKNOWNEXPLOIT AVAIL

Subrion CMS: stored XSS in admin config panel

CVE-2020-18325
--
EPSS 1.6%
Code ExecutionAuth BypassPlugin
UNKNOWNEXPLOIT AVAIL

Zepl Notebooks: RCE via malicious notebook code

CVE-2021-42950
--
EPSS 1.6%
Code ExecutionFramework
2 ATLAS
UNKNOWNEXPLOIT AVAIL

Zepl Notebooks: sandbox escape exposes cloud metadata

CVE-2021-42952
--
EPSS 1.6%
Code ExecutionData LeakageFramework
4 ATLAS
HIGHEXPLOIT AVAIL

MLflow: insecure temp file handling causes DoS

CVE-2022-0736
7.5
EPSS 1.6%
DoSFrameworkTraining Data
mlflow6953 ATLAS
UNKNOWNEXPLOIT AVAIL

XMPie UStore: persistent XSS in admin user panel

CVE-2022-23321
--
EPSS 0.6%
Code ExecutionPrivacy ViolationFramework
MEDIUMEXPLOIT AVAIL

TensorFlow XLA: null pointer dereference causes DoS

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

TensorFlow MLIR-TFRT: DoS via scalar shape segfault

CVE-2022-23593
7.5
EPSS 0.9%
DoSFrameworkInference
tensorflowCWE-7543.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB read in type inference engine

CVE-2022-23592
8.1
EPSS 0.9%
Data ExtractionDoSCode ExecutionFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: SavedModel stack overflow via recursive GraphDef

CVE-2022-23591
7.5
EPSS 0.8%
DoSSupply ChainFrameworkModel
tensorflowCWE-6743.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: DoS via malicious SavedModel GraphDef

CVE-2022-23590
7.5
EPSS 1.0%
DoSSupply ChainFrameworkModelInference
tensorflow3.4K4 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
CRITICALEXPLOIT AVAIL

TensorFlow: integer overflow in Grappler enables RCE

CVE-2022-23587
9.8
EPSS 0.9%
Code ExecutionDoSFrameworkInference
tensorflowCWE-1903.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: SavedModel DoS crashes Python interpreter

CVE-2022-23586
6.5
EPSS 0.8%
DoSFrameworkModel
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