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
3,591

AI/ML CVEs Tracked

481

Critical

84

New This Week

24

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 2346 results — no patch
HIGH

SolidUI: OpenAI API key exposed via log print statement

CVE-2024-34527
7.5
EPSS 0.5%
Data Leakage Data Extraction API Framework
5 ATLAS
HIGH EXPLOIT AVAIL

Gradio: credential leakage via Windows path encoding bug

CVE-2024-34510
7.5
EPSS 0.6%
Data Leakage Data Extraction Framework Inference API
gradio CWE-116 721 5 ATLAS
HIGH

SageMaker SDK: pickle deserialization enables RCE

CVE-2024-34072
7.8
EPSS 0.4%
Code Execution Supply Chain Framework Training Data
4 ATLAS
MEDIUM

Quarkus RESTEasy: DoS via late-stage auth checks

CVE-2024-1726
5.3
EPSS 0.7%
DoS API
3 ATLAS
MEDIUM

PyTorch: OOB read in mobile model loader leaks memory

CVE-2024-31584
5.5
EPSS 0.4%
Supply Chain Data Extraction Framework Model
pytorch 25.2K 5 ATLAS
HIGH

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

CVE-2024-31583
7.8
EPSS 0.3%
Supply Chain Code Execution Framework Inference
pytorch 25.2K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: heap buffer overflow causes local DoS

CVE-2024-31580
4.0
EPSS 0.2%
DoS Framework
pytorch 25.2K 3 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 1.5K 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-22 690 5 ATLAS
HIGH EXPLOIT AVAIL

LangChain: path traversal allows arbitrary file R/W

CVE-2024-3571
8.8
EPSS 1.9%
Code Execution Data Extraction Framework Agent
langchain 3.0K 6 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
HIGH EXPLOIT AVAIL

MLflow: path traversal via URI fragment reads arbitrary files

CVE-2024-1594
7.5
EPSS 0.7%
Data Extraction Data Leakage Framework Training Data
mlflow 690 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: path traversal via ';' smuggling exposes files

CVE-2024-1593
7.5
EPSS 0.7%
Data Extraction Auth Bypass Framework Training Data
mlflow 690 4 ATLAS
UNKNOWN KEV SCANNER

Gradio: path traversal enables arbitrary file read

CVE-2024-1561
--
EPSS 9.3%
Data Extraction Data Leakage Framework API
gradio 721 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: path traversal allows arbitrary directory deletion

CVE-2024-1560
8.1
EPSS 0.9%
Supply Chain DoS Auth Bypass Framework Training Data
mlflow 690 3 ATLAS
HIGH EXPLOIT AVAIL

MLflow: path traversal enables arbitrary file read

CVE-2024-1558
7.5
EPSS 0.9%
Data Extraction Data Leakage Framework
mlflow 690 5 ATLAS
HIGH EXPLOIT AVAIL SCANNER

MLflow: path traversal exposes arbitrary server files

CVE-2024-1483
7.5
EPSS 2.7%
Data Extraction Auth Bypass Framework Training Data
mlflow 690 5 ATLAS
UNKNOWN EXPLOIT AVAIL SCANNER

Gradio: SSRF enables internal network port scanning

CVE-2024-1183
--
EPSS 1.8%
Data Extraction Privacy Violation Framework Inference
gradio 721 3 ATLAS
MEDIUM

stable-diffusion-webui: path traversal file write

CVE-2024-31462
6.3
EPSS 0.7%
Code Execution Framework Inference
3 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 9.5K 5 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