Scholarlink

<p>As the semiconductor industry has shifted to a fabless paradigm, the risk of hardware Trojans being inserted at various stages of production has also increased. Recently, there has been a growing trend toward the use of machine learning solutions to effectively detect hardware Trojans with a focus on the accuracy of the model as an evaluation metric. However, in a high-risk and sensitive domain, we cannot accept even a small misclassification. Additionally, it is unrealistic to expect an ideal model, especially when Trojans evolve over time. In this paper, we design an uncertainty-aware machine learning solution which also handles evolving hardware Trojans using our proposed novel conformalized generative adversarial network. We further extend the proposed method for multimodal deep learning along with uncertainty quantification that also addresses the problem of missing modalities. The proposed solutions have been validated on both synthetic and real chip-level benchmarks and proven to pave the way for researchers looking to find informed machine learning solutions to hardware security problems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Uncertainty-Aware Unimodal and Multimodal Learning for Evolving Hardware Trojan Detection

  • 期刊论文

  • 发表日期：

    2025年2月26日

查看全文
  • Rahul Vishwakarma,
  • Amin Rezaei

摘要

As the semiconductor industry has shifted to a fabless paradigm, the risk of hardware Trojans being inserted at various stages of production has also increased. Recently, there has been a growing trend toward the use of machine learning solutions to effectively detect hardware Trojans with a focus on the accuracy of the model as an evaluation metric. However, in a high-risk and sensitive domain, we cannot accept even a small misclassification. Additionally, it is unrealistic to expect an ideal model, especially when Trojans evolve over time. In this paper, we design an uncertainty-aware machine learning solution which also handles evolving hardware Trojans using our proposed novel conformalized generative adversarial network. We further extend the proposed method for multimodal deep learning along with uncertainty quantification that also addresses the problem of missing modalities. The proposed solutions have been validated on both synthetic and real chip-level benchmarks and proven to pave the way for researchers looking to find informed machine learning solutions to hardware security problems.