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 1961 results — Active exploitation
HIGHEXPLOIT AVAIL

MLflow: RCE via deserialization in crafted Recipes

CVE-2024-37060
8.8
EPSS 0.8%
Code ExecutionSupply ChainFrameworkTraining Data
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious PyTorch model deserialization

CVE-2024-37059
8.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkModel
mlflowCWE-5026954 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious LangChain model deserialization

CVE-2024-37058
8.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModelAgent
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious TensorFlow model deserialization

CVE-2024-37057
8.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModel
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via LightGBM model deserialization

CVE-2024-37056
8.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModel
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via pmdarima model deserialization

CVE-2024-37055
8.8
EPSS 0.6%
Code ExecutionSupply ChainFrameworkModel
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: deserialization RCE via malicious PyFunc model

CVE-2024-37054
8.8
EPSS 0.7%
Supply ChainCode ExecutionFrameworkModel
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious scikit-learn model deserialization

CVE-2024-37053
8.8
EPSS 0.6%
Supply ChainCode ExecutionFrameworkModel
mlflowCWE-5026955 ATLAS
HIGHEXPLOIT AVAIL

MLflow: RCE via malicious scikit-learn model upload

CVE-2024-37052
8.8
EPSS 0.7%
Code ExecutionSupply ChainFrameworkModel
mlflowCWE-5026955 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: CI/CD command injection enables secrets exfiltration

CVE-2024-4253
9.1
EPSS 1.7%
Supply ChainCode ExecutionData ExtractionFrameworkInferenceAPI
gradio7355 ATLAS
HIGHKEV

Ollama: path traversal enables RCE via model blob API

CVE-2024-37032
8.8
EPSS 89.6%
Code ExecutionData ExtractionInferenceFrameworkAPI
ollama1.9K4 ATLAS
UNKNOWNEXPLOIT AVAIL

text-generation-inference: workflow injection RCE

CVE-2024-3924
--
EPSS 0.3%
Supply ChainCode ExecutionFrameworkInference
4 ATLAS
MEDIUMEXPLOIT AVAIL

WP Testimonial Carousel: OpenAI API key hijack, no auth

CVE-2024-4858
5.3
EPSS 0.4%
Auth BypassDoSAPIPlugin
CWE-8624 ATLAS
HIGHEXPLOIT AVAIL

WordPress AI ChatBot: auth bypass enables OpenAI file upload

CVE-2024-0452
7.7
EPSS 0.4%
Auth BypassData LeakageModel PoisoningAPIPlugin
wpbotCWE-8625 ATLAS
MEDIUMEXPLOIT AVAIL

wpbot: missing auth exposes OpenAI account files

CVE-2024-0451
5.0
EPSS 0.4%
Data ExtractionAuth BypassAPIPlugin
wpbotCWE-8625 ATLAS
MEDIUMEXPLOIT AVAIL

MLflow: broken access control allows artifact deletion

CVE-2024-4263
5.4
EPSS 0.3%
Auth BypassFrameworkTraining Data
mlflow6953 ATLAS
UNKNOWNEXPLOIT AVAIL

llama_index: RCE via eval() in RunGptLLM connector

CVE-2024-4181
--
EPSS 2.1%
Code ExecutionSupply ChainFrameworkInference
llamaindex3 ATLAS
HIGHEXPLOIT AVAILSCANNER

MLflow: URL fragment bypass leaks SSH and cloud keys

CVE-2024-3848
7.5
EPSS 43.3%
Data ExtractionAuth BypassFramework
mlflowCWE-226954 ATLAS
CRITICALEXPLOIT AVAIL

llama-cpp-python: SSTI in .gguf loader enables RCE

CVE-2024-34359
9.6
EPSS 26.0%
Code ExecutionSupply ChainFrameworkModelInference
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

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