On the Efficacy and Vulnerabilities of Logic Locking in Tree-Based Machine Learning

Brunno Alves De Abreu, Guilherme Paim, Lilas Alrahis, Paulo Flores, Ozgur Sinanoglu, Sergio Bampi, Hussam Amrouch

Research output: Contribution to journalArticlepeer-review

Abstract

The popularity and widespread usage of machine learning (ML) hardware have created challenges for its intellectual property (IP) protection. Logic locking is a widely used technique for IP protection but has received little attention in error-resilient applications such as ML hardware modules. This work investigates the effectiveness of logic locking when applied to tree-based ML circuits and reveals a critical vulnerability that undermines its effectiveness for single-label ML classifiers. We propose a logic locking scheme to eliminate the vulnerabilities in decision trees (DTs) and random forests (RFs) circuits. In our extensive simulation involving 16 DTs and 16 RFs, our solution consistently thwarts the vulnerability. We further evaluated the security of our approach by considering different obfuscation percentages and launching state-of-the-art oracle-less attacks on logic locking. Our method proves resilient, indicating that by fixing the identified vulnerability, we did not introduce new attack vectors. Further, our investigation indicates that DT/RF accelerators are significantly less vulnerable to oracle-less attacks compared to exact circuits. Overall, our work lays the foundation for future investigations into the effectiveness of logic locking for ML circuits.

Original languageEnglish (US)
Pages (from-to)180-191
Number of pages12
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Volume72
Issue number1
DOIs
StatePublished - 2025

Keywords

  • Logic locking
  • decision trees
  • hardware security
  • machine learning
  • random forest

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'On the Efficacy and Vulnerabilities of Logic Locking in Tree-Based Machine Learning'. Together they form a unique fingerprint.

Cite this