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

95

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
HIGH

SolidUI: OpenAI API key exposed via log print statement

CVE-2024-34527
7.5
EPSS 0.5%
Data LeakageData ExtractionAPIFramework
5 ATLAS
HIGHEXPLOIT AVAIL

Gradio: credential leakage via Windows path encoding bug

CVE-2024-34510
7.5
EPSS 0.7%
Data LeakageData ExtractionFrameworkInferenceAPI
gradioCWE-1167355 ATLAS
HIGH

SageMaker SDK: pickle deserialization enables RCE

CVE-2024-34072
7.8
EPSS 0.4%
Code ExecutionSupply ChainFrameworkTraining Data
4 ATLAS
MEDIUMEXPLOIT AVAIL

Quarkus RESTEasy: DoS via late-stage auth checks

CVE-2024-1726
5.3
EPSS 0.7%
DoSAPI
3 ATLAS
MEDIUM

Quarkus: JAX-RS authorization not enforced on methods

CVE-2023-5675
6.5
EPSS 0.5%
Auth BypassData LeakageAPIFramework
2 ATLAS
MEDIUM

PyTorch: OOB read in mobile model loader leaks memory

CVE-2024-31584
5.5
EPSS 0.4%
Supply ChainData ExtractionFrameworkModel
pytorch26.1K5 ATLAS
HIGH

PyTorch: use-after-free in JIT mobile interpreter, RCE

CVE-2024-31583
7.8
EPSS 0.3%
Supply ChainCode ExecutionFrameworkInference
pytorch26.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: heap buffer overflow causes local DoS

CVE-2024-31580
4.0
EPSS 0.2%
DoSFramework
pytorch26.1K3 ATLAS
CRITICALEXPLOIT AVAIL

Keras: RCE via malicious model deserialization

CVE-2024-3660
9.8
EPSS 1.7%
Code ExecutionSupply ChainFrameworkModel
kerasCWE-944.1K5 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: LFI via URI parsing allows arbitrary file read

CVE-2024-3573
9.3
EPSS 0.7%
Data ExtractionAuth BypassFramework
mlflowCWE-226955 ATLAS
HIGHEXPLOIT AVAIL

LangChain: path traversal allows arbitrary file R/W

CVE-2024-3571
8.8
EPSS 1.9%
Code ExecutionData ExtractionFrameworkAgent
langchain3.2K6 ATLAS
CRITICALEXPLOIT AVAIL

BentoML: RCE via insecure deserialization (CVSS 10)

CVE-2024-2912
10.0
EPSS 1.5%
Code ExecutionSupply ChainFrameworkInference
5 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal via URI fragment reads arbitrary files

CVE-2024-1594
7.5
EPSS 0.7%
Data ExtractionData LeakageFrameworkTraining Data
mlflow6955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal via ';' smuggling exposes files

CVE-2024-1593
7.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkTraining Data
mlflow6954 ATLAS
UNKNOWNKEVSCANNER

Gradio: path traversal enables arbitrary file read

CVE-2024-1561
--
EPSS 9.3%
Data ExtractionData LeakageFrameworkAPI
gradio7355 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal allows arbitrary directory deletion

CVE-2024-1560
8.1
EPSS 0.9%
Supply ChainDoSAuth BypassFrameworkTraining Data
mlflow6953 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal enables arbitrary file read

CVE-2024-1558
7.5
EPSS 0.9%
Data ExtractionData LeakageFramework
mlflow6955 ATLAS
HIGHEXPLOIT AVAILSCANNER

MLflow: path traversal exposes arbitrary server files

CVE-2024-1483
7.5
EPSS 2.7%
Data ExtractionAuth BypassFrameworkTraining Data
mlflow6955 ATLAS
UNKNOWNEXPLOIT AVAILSCANNER

Gradio: SSRF enables internal network port scanning

CVE-2024-1183
--
EPSS 1.8%
Data ExtractionPrivacy ViolationFrameworkInference
gradio7353 ATLAS
MEDIUM

stable-diffusion-webui: path traversal file write

CVE-2024-31462
6.3
EPSS 0.7%
Code ExecutionFrameworkInference
3 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