POLARIS: Explainable Artificial Intelligence for Mitigating Power Side-Channel Leakage

2025-07-29

AI Summary

Dynamic power consumption in microelectronic systems induces power side-channel leakage—enabling adversaries to infer cryptographic keys. To address this, we propose an unsupervised masking defense framework grounded in eXplainable Artificial Intelligence (XAI). Our method requires no labeled training data; instead, XAI techniques automatically interpret power traces to guide the design of masking strategies, enabling joint optimization of synthetic trace generation and masking model training. The key contribution lies in the deep integration of XAI into the hardware security workflow—achieving, for the first time, a fully label-free, interpretable, and end-to-end side-channel suppression solution. Experimental evaluation demonstrates that our framework significantly outperforms state-of-the-art approaches (e.g., VALIANT) across three critical metrics: leakage suppression rate, execution speed, and hardware overhead—thereby offering superior security, efficiency, and resource efficiency.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Microelectronic systems are widely used in many sensitive applications (e.g., manufacturing, energy, defense). These systems increasingly handle sensitive data (e.g., encryption key) and are vulnerable to diverse threats, such as, power side-channel attacks, which infer sensitive data through dynamic power profile. In this paper, we present a novel framework, POLARIS for mitigating power side channel leakage using an Explainable Artificial Intelligence (XAI) guided masking approach. POLARIS uses an unsupervised process to automatically build a tailored training dataset and utilize it to train a masking model.The POLARIS framework outperforms state-of-the-art mitigation solutions (e.g., VALIANT) in terms of leakage reduction, execution time, and overhead across large designs.

Problem

• Mitigate power side-channel leakage using XAI
• Automatically build tailored training dataset
• Outperform state-of-the-art mitigation solutions

Innovation

• XAI-guided masking for power leakage
• Unsupervised tailored dataset creation
• Superior leakage reduction and efficiency