PAI-favicon-120423 MLSecOps-favicon icon3

Protect AI Threat Research

Read our reports and findings on the most up to date threats in the AI/ML space.

Vulnhuntr: Autonomous AI Finds First 0-Day Vulnerabilities in Wild

Introduction Today, we introduce Vulnhuntr, a Python static code analyzer that leverages the power of large language models (LLMs) to find and explain complex, multistep vulnerabilities. Thanks to the capabilities of models like Claude 3.5, AI has no...

Read on

The Best of Protect AI's Threat Research

Keep up with the latest articles from Protect AI