Protect AI Blog

Red Teaming

May 7, 2025

GPT-4.1 Assessment: Critical Vulnerabilities Exposed

GPT-4.1 Mini earns the highest risk score after latest update Assessment Brief OpenAI has...

12 minute read

Read more

Machine Learning

April 16, 2025

Machine Learning Models: A New Attack Vector for an Old Exploit

Machine learning (ML) has seen rapid adoption across industries, enabling advancements in...

6 minute read

Read more

Red Teaming

April 2, 2025

Qwen2.5-Max Vulnerability Assessment

Qwen2.5-Max beats DeepSeek-V3 on Security Assessment Brief The model used for this assessment,

15 minute read

Read more

Threat Intelligence

June 20, 2024

Navigating Vulnerabilities in the AI Supply Chain

Introduction In the second chapter of navigating AI/ML security concerns, let’s explore Adam...

6 minute read

Read more

Threat Intelligence

June 6, 2023

Secure Your Python Projects with Dummies

TL;DR If you use a private package index for a Python library in development, ensure that it...

7 minute read

Read more

Threat Intelligence

June 5, 2023

Hacking AI: System Takeover in MLflow Strikes Again (And Again)

2 patch bypasses found for severe MLflow LFI/RFI vulnerability All patched in MLflow version...

13 minute read

Read more

Threat Intelligence

March 7, 2023

AI Zero Day Found in MLflow

AIØD: MLflow Could Expose Entire ML System TL;DR: MLflow versions prior to 2.2.2 have AI...

9 minute read

Read more

Threat Intelligence

March 6, 2023

Hacking AI: Steal Models from MLflow, No Exploit Needed

No Authentication Can Lead To Problems MLflow comes with no authentication out of the box...

10 minute read

Read more