AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

New This Week

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 766 results — Active exploitation, no patch

MEDIUM EXPLOIT AVAIL

wpbot: missing auth exposes OpenAI account files

Data Extraction Auth Bypass API Plugin

wpbot CWE-862 5 ATLAS

MEDIUM EXPLOIT AVAIL

MLflow: broken access control allows artifact deletion

Auth Bypass Framework Training Data

mlflow 624 3 ATLAS

UNKNOWN EXPLOIT AVAIL

llama_index: RCE via eval() in RunGptLLM connector

CVE-2024-4181

EPSS 1.6%

1y ago

Code Execution Supply Chain Framework Inference

llamaindex 3 ATLAS

HIGH EXPLOIT AVAIL SCANNER

MLflow: URL fragment bypass leaks SSH and cloud keys

Data Extraction Auth Bypass Framework

mlflow CWE-22 624 4 ATLAS

CRITICAL EXPLOIT AVAIL

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

Code Execution Supply Chain Framework Model Inference

5 ATLAS

HIGH EXPLOIT AVAIL

Gradio: credential leakage via Windows path encoding bug

Data Leakage Data Extraction Framework Inference API

gradio CWE-116 679 5 ATLAS

MEDIUM EXPLOIT AVAIL

PyTorch: heap buffer overflow causes local DoS

pytorch 21.9K 3 ATLAS

CRITICAL EXPLOIT AVAIL

Keras: RCE via malicious model deserialization

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

Data Extraction Auth Bypass Framework

mlflow CWE-22 624 5 ATLAS

HIGH EXPLOIT AVAIL

LangChain: path traversal allows arbitrary file R/W

Code Execution Data Extraction Framework Agent

langchain 2.6K 6 ATLAS

CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization (CVSS 10)

Code Execution Supply Chain Framework Inference

5 ATLAS

HIGH EXPLOIT AVAIL

MLflow: path traversal via URI fragment reads arbitrary files

Data Extraction Data Leakage Framework Training Data

mlflow 624 5 ATLAS

HIGH EXPLOIT AVAIL

MLflow: path traversal via ';' smuggling exposes files

Data Extraction Auth Bypass Framework Training Data

mlflow 624 4 ATLAS

UNKNOWN KEV SCANNER

Gradio: path traversal enables arbitrary file read

CVE-2024-1561

EPSS 93.4%

2y ago

Data Extraction Data Leakage Framework API

gradio 679 5 ATLAS

HIGH EXPLOIT AVAIL

MLflow: path traversal allows arbitrary directory deletion

Supply Chain DoS Auth Bypass Framework Training Data

mlflow 624 3 ATLAS

HIGH EXPLOIT AVAIL

MLflow: path traversal enables arbitrary file read

Data Extraction Data Leakage Framework

mlflow 624 5 ATLAS

HIGH EXPLOIT AVAIL SCANNER

MLflow: path traversal exposes arbitrary server files

Data Extraction Auth Bypass Framework Training Data

mlflow 624 5 ATLAS

UNKNOWN EXPLOIT AVAIL SCANNER

Gradio: SSRF enables internal network port scanning

CVE-2024-1183

EPSS 55.0%

2y ago

Data Extraction Privacy Violation Framework Inference

gradio 679 3 ATLAS

CRITICAL EXPLOIT AVAIL

HuggingFace Transformers: RCE via pickle deserialization

Code Execution Supply Chain Framework Model

transformers 7.9K 5 ATLAS

HIGH EXPLOIT AVAIL SCANNER

Gradio: path traversal leaks arbitrary files, potential RCE

Data Extraction Code Execution Privacy Violation Framework API Inference

gradio 679 6 ATLAS

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

AI Security Threat Feed

Weekly CISO Take + top threats

Latest AI Security Threats

Need deeper analysis?