INSIGHT: Attacking Industry-Adopted Learning Resilient Logic Locking Techniques Using Explainable Graph Neural Network
Lakshmi Likhitha Mankali, Ozgur Sinanoglu, Satwik Patnaik
33rd USENIX Security Symposium · Day 1 · USENIX Security '24
In an era defined by a globalized IC supply chain, hardware security vulnerabilities have become a paramount concern, particularly **Hardware IP piracy**. This talk, presented by Lakshmi Likhitha Mankali, Ozgur Sinanoglu, and Satwik Patnaik, delves into the critical challenge of protecting integrated circuit (IC) designs from malicious actors within the supply chain. Logic locking has emerged as a prominent defense mechanism, gaining significant traction and investment from both government programs like DARPA's ACE, ECLIPSE, and SAHARA, and commercial entities like Synopsys and Mentor Graphics, who have integrated it into their Electronic Design Automation (EDA) tools. However, the rise of sophisticated machine learning (ML) based attacks has prompted the development of "learning resilient" logic locking techniques, specifically designed to thwart these structural inference attacks.
AI review
This research delivers a brutal, much-needed reality check to hardware IP protection. INSIGHT leverages Explainable GNNs to tear through 'learning resilient' logic locking, including industry-adopted schemes, by re-framing the key prediction problem. It's a fundamental shift in attack methodology that exposes critical vulnerabilities in current defenses and forces an immediate re-evaluation of the entire paradigm.