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 160 results — Critical severity, Active exploitation

CRITICAL EXPLOIT AVAIL

Gradio: path traversal + SSRF exposes model files & infra

Data Extraction Privacy Violation Auth Bypass Framework API

gradio 674 5 ATLAS

CRITICAL EXPLOIT AVAIL SCANNER

MLflow: path traversal allows arbitrary file read/write

Data Extraction Code Execution Supply Chain Framework Training Data Model

mlflow 624 5 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via prompt injection in LLMMathChain

Prompt Injection Code Execution Framework Agent

langchain CWE-74 2.6K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: unauthenticated RCE via heap buffer overflow

Code Execution DoS Framework Inference

tensorflow 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: heap overflow in AvgPoolGrad, RCE risk

Code Execution Supply Chain Framework Inference

tensorflow 3.7K 4 ATLAS

CRITICAL KEV SCANNER

MLflow: path traversal allows arbitrary file read/write

Data Extraction Code Execution Supply Chain Framework Model Training Data

mlflow 624 7 ATLAS

CRITICAL EXPLOIT AVAIL

Gradio: hardcoded SSH key leaks via share=True demos

Auth Bypass Data Extraction Privacy Violation Framework Inference

gradio CWE-798 674 5 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow Grappler: OOB read/crash via crafted model

DoS Data Extraction Framework Inference

tensorflow CWE-125 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

PyTorch: RCE via unsafe eval in JIT annotations

Code Execution Supply Chain Framework Inference

pytorch CWE-94 21.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: heap OOB RCE in FractionalMaxPool op

Code Execution DoS Framework Inference

tensorflow 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: heap OOB read in candidate sampler op

Data Extraction DoS Code Execution Framework Inference Training Data

tensorflow 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

pytorch-lightning: code injection enables full RCE

Code Execution Supply Chain Framework Training Data

pytorch_lightning CWE-94 21.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: integer overflow in Grappler enables RCE

Code Execution DoS Framework Inference

tensorflow CWE-190 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: path traversal in get_file allows file overwrite

Supply Chain Code Execution Framework Training Data

tensorflow CWE-22 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TFLite: OOB read/write via tensor dimension mismatch

Code Execution Data Extraction Supply Chain Framework Inference

tensorflow 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

TFLite: OOB write via unchecked negative axis index

Code Execution DoS Framework Inference

tensorflow CWE-787 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: heap overflow in StringNGrams, ASLR bypass

Code Execution Data Leakage Framework Inference

tensorflow CWE-787 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: Shard API int truncation enables memory corruption

Code Execution DoS Framework Inference

tensorflow 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

TensorFlow: heap OOB read in sparse/ragged count ops

Code Execution Data Extraction Framework Inference Training Data

tensorflow CWE-125 3.7K 4 ATLAS

CRITICAL EXPLOIT AVAIL

scikit-learn: RCE via malicious joblib model deserialization

Code Execution Supply Chain Framework Model

scikit-learn CWE-502 27.9K 5 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?