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

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, allowi

Categories

Framework mappings

Suggested from the entry's categories.

@misc{rezakhani2026rtlguard,
  title = {{RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models}},
  author = {Mahshid Rezakhani and K. Azar and H. Kamali},
  year = {2026},
  month = aug,
  eprint = {2608.26049},
  archivePrefix = {arXiv},
  doi = {10.1145/3831252.3834219},
  url = {https://www.semanticscholar.org/paper/905f1889d0ef658a604096a02d0026afb21ee4f7}
}