RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models

2026-08-26

AI Summary

为解决预训练模型在RTL代码生成中可能引入的隐藏后门威胁，RTLGuard采用教师-学生框架，通过知识蒸馏和特征对齐方法抑制恶意行为。

Abstract

The rapid advancement of large language models (LLMs) is driving a shift toward automated register transfer level (RTL) code generation, enabling designers to translate high-level specs. into synthesizable hardware. However, this reliance on pre-trained (3rd-party) fine-tuned models may introduce critical trust issues, as the training data and adaptation process of these models are often opaque. Thus, adversaries (even model providers) may embed hidden backdoor threats during fine-tuning, allowing malicious behavior, e.g., hardware Trojans, to be triggered by seemingly benign prompts given by victim user at inference time. In this paper, we introduce RTLGuard, to mitigate such a trust issue in AI-enabled IC supply chain. Rather than prohibitive computational cost of full-parameter retraining, RTLGuard leverages a teacher-student framework designed to sanitize compromised RTL generation models by (1) fine-tuning a small-scale, "clean" teacher model on a limited set of trusted RTL data, (2) guiding the poisoned target model via a composite teacher-student objective, and (3) incorporating feature alignment and knowledge distillation to suppress malicious behaviors. Our experiments across various LLM architectures demonstrate that RTLGuard significantly reduces the Attack Success Rate (ASR) while preserving the functional correctness and synthesizability of the generated RTL code.

Problem

• large language models
• automated RTL code generation
• trust issues
• hidden backdoor threats
• malicious behavior

Innovation

• Teacher-Student Framework
• Feature Alignment
• Knowledge Distillation
• RTL Code Generation
• Backdoor Threat Mitigation