Aggregator

Machine Learning Attack Series: Backdooring Keras Models and How to Detect It

Embrace The Red
1 year 11 months ago

This post is part of a series about machine learning and artificial intelligence.

Adversaries often leverage supply chain attacks to gain footholds. In machine learning model deserialization issues are a significant threat, and detecting them is crucial, as they can lead to arbitrary code execution. We explored this attack with Python Pickle files in the past.

In this post we are covering backdooring the original Keras Husky AI model from the Machine Learning Attack Series, and afterwards we investigate tooling to detect the backdoor.

SCCM / MECM LAB - Part 0x0

Mayfly - Hack, Code, Sleep, Repeat
1 year 11 months ago
Some time ago i discovered the work of some researchers about SCCM, i was very interested by their research and as i reading i thought that i really need a lab to test all these cool attacks ! Thanks a lot to my colleague Issam (@KenjiEndo15), who start the project and provide me some of ansible roles to start from ! After few hours, days, weeks of install, ansible recipe creation, try and ...
mayfly

Managed ad