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
2,388

AI/ML CVEs Tracked

342

Critical

358

New This Week

18

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 342 results — Critical severity
CRITICAL EXPLOIT AVAIL SCANNER

ChuanhuChatGPT: path traversal exposes LLM API keys

CVE-2024-3234
9.8
EPSS 3.8%
Data Extraction Auth Bypass Data Leakage Framework API
chuanhuchatgpt 5 ATLAS
CRITICAL EXPLOIT AVAIL

pytorch-lightning: RCE via deepdiff Delta deserialization

CVE-2024-5452
9.8
EPSS 26.5%
Code Execution Supply Chain Framework
pytorch_lightning CWE-913 22.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

Gradio: CI/CD command injection enables secrets exfiltration

CVE-2024-4253
9.1
EPSS 1.7%
Supply Chain Code Execution Data Extraction Framework Inference API
gradio 685 5 ATLAS
CRITICAL EXPLOIT AVAIL

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

CVE-2024-34359
9.6
EPSS 28.4%
Code Execution Supply Chain Framework Model Inference
5 ATLAS
CRITICAL EXPLOIT AVAIL

Keras: RCE via malicious model deserialization

CVE-2024-3660
9.8
EPSS 1.7%
Code Execution Supply Chain Framework Model
keras CWE-94 1.6K 5 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: LFI via URI parsing allows arbitrary file read

CVE-2024-3573
9.3
EPSS 0.7%
Data Extraction Auth Bypass Framework
mlflow CWE-22 655 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization (CVSS 10)

CVE-2024-2912
10.0
EPSS 1.5%
Code Execution Supply Chain Framework Inference
5 ATLAS
CRITICAL EXPLOIT AVAIL

HuggingFace Transformers: RCE via pickle deserialization

CVE-2024-3568
9.6
EPSS 2.1%
Code Execution Supply Chain Framework Model
transformers 8.3K 5 ATLAS
CRITICAL EXPLOIT AVAIL

gpt_academic: deserialization RCE, no auth required

CVE-2024-31224
9.8
EPSS 1.2%
Code Execution Data Extraction Framework API
gpt_academic 5 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain TFIDFRetriever: SSRF/RCE via load_local

CVE-2024-2057
9.8
EPSS 0.6%
Code Execution Data Extraction Framework RAG
langchain 2.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain Experimental: RCE via Python sandbox escape

CVE-2024-27444
9.8
EPSS 0.8%
Code Execution Supply Chain Framework Agent
langchain-experimental 2.7K 4 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: XSS in recipe runner enables Jupyter RCE

CVE-2024-27133
9.6
EPSS 0.7%
Code Execution Supply Chain Framework
mlflow 655 5 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: XSS in recipes enables client-side RCE

CVE-2024-27132
9.6
EPSS 0.9%
Code Execution Supply Chain Data Extraction Framework Training Data
mlflow 655 5 ATLAS
CRITICAL EXPLOIT AVAIL

Gradio: unauthenticated LFI exposes full server filesystem

CVE-2024-0964
9.4
EPSS 1.0%
Data Extraction Data Leakage Auth Bypass Framework Inference API
gradio CWE-22 685 5 ATLAS
CRITICAL EXPLOIT AVAIL

LlamaIndex: SQL injection in Text-to-SQL feature

CVE-2024-23751
9.8
EPSS 0.7%
Code Execution Data Extraction Prompt Injection Framework Agent
llamaindex CWE-89 5 ATLAS
CRITICAL KEV SCANNER

Ray: unauthenticated RCE via job submission API

CVE-2023-48022
9.8
EPSS 81.5%
Code Execution Auth Bypass Framework Training Data Inference
ray CWE-829 873 6 ATLAS
CRITICAL EXPLOIT AVAIL SCANNER

Ray: unauthenticated LFI exposes entire filesystem

CVE-2023-6020
9.3
EPSS 14.7%
Data Extraction Auth Bypass Framework Training Data Model
ray Patch: 2.8.1 CWE-598 873 5 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: auth bypass allows arbitrary account creation

CVE-2023-6014
9.8
EPSS 1.2%
Auth Bypass Data Extraction Supply Chain Framework Training Data Model
mlflow 655 6 ATLAS
CRITICAL EXPLOIT AVAIL SCANNER

Ray: LFI allows unauthenticated file read

CVE-2023-6021
9.3
EPSS 37.1%
Data Extraction Auth Bypass Framework Inference
ray Patch: 2.8.1 CWE-22 873 5 ATLAS
CRITICAL EXPLOIT AVAIL

Ray: unauthenticated RCE via dashboard command injection

CVE-2023-6019
9.8
EPSS 74.6%
Code Execution Auth Bypass Supply Chain Framework Inference Training Data
ray Patch: 2.8.1 CWE-78 873 6 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