paperAugust 2026Unreviewed

Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation

Guang Yang, Xing Hu, Xiang Chen, Xin Xia

Abstract

Large Language Models (LLMs) generate register-transfer-level (RTL) code with rapidly improving functional correctness. Security of LLM-generated code, however, has been studied mainly for software, where flaws can still be patched after deployment. Insecure RTL offers no such remedy once taped out into silicon. We construct SECRTL-GEN, a multi-language resource-access security benchmark grounded in real SoC IP: 392 tasks over five CWE families and four HDLs (Verilog, SystemVerilog, VHDL, and Py

Cite

@misc{yang2026unsaid,
  title = {{Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation}},
  author = {Guang Yang and Xing Hu and Xiang Chen and Xin Xia},
  year = {2026},
  month = aug,
  eprint = {2608.26588},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.26588}
}