Zeng Wang

Minghao Shao, Zeng Wang, Weimin Fu et al.

Benchmarking of open-source LLMs for hardware design focuses on which LLMs to use, while treating inference-time decoding configuration as a secondary concern. This work shows that it matters more how an LLM is configured than which model is selected. Benchmarking 26 open-source LLMs on VerilogEval and RTLLM with synthesis-in-the-loop evaluation, the study first maps the current capability landscape and then conducts an extensive 108-configuration hyperparameter sweep on three prominent models. The sweep reveals absolute pass-rate gaps of up to 25.5% between the best and worst settings for the same LLM, which is 5x larger than the average spread observed across various model families under their respective default configurations. Ranking all configurations by Spearman's $ρ$ across the two benchmark suites yields near-zero correlation, demonstrating that optimal configurations do not transfer. These results show that benchmarking conducted under default hyperparameters confounds model capabilities with configuration effects. Realizing the full potential of open-source LLMs for RTL generation requires architecture and benchmark aware hyperparameter selection, as enabled by the proposed methodology.

Zeng Wang, Minghao Shao, Weimin Fu et al.

The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design optimization, but also raises critical security concerns. Malicious LLM outputs in this domain pose hardware-level threats, including hardware Trojan insertion, side-channel leakage, and intellectual property theft, that are irreversible once fabricated into silicon. Such requests often exploit semantic disguise, embedding adversarial intent within legitimate engineering language that existing safety mechanisms, trained on general-purpose hazards, fail to detect. No benchmark exists to evaluate LLM vulnerability to such domain-specific threats. We present the HarmChip benchmark to assess jailbreak susceptibility in hardware security, spanning 16 hardware security domains, 120 threats, and 360 prompts at two difficulty levels. Evaluation of state-of-the-art LLMs reveals an alignment paradox: They refuse legitimate security queries while complying with semantically disguised attacks, exposing blind spots in safety guardrails and underscoring the need for domain-aware safety alignment.

Weimin Fu, Zeng Wang, Minghao Shao et al.

Edge applications increasingly demand custom hardware, yet Field-Programmable Gate Array (FPGA) design requires expertise that domain engineers lack. Large Language Models (LLMs) promise to bridge this gap through zero-knowledge hardware programming, where users describe circuits in natural language and an LLM compiles them to a hardware intermediate representation (IR) targeting silicon. Modeling this flow as a cascade of binary filters, this work demonstrates that IR choice, not model choice, is the dominant factor governing end-to-end success, a phenomenon termed the representation bottleneck. An evaluation of three frontier LLMs across six IRs spanning Verilog, VHDL, Chisel, Bluespec, PyMTL3, and HLS C on 202 tasks through a pipeline of compilation, simulation, FPGA synthesis on a Lattice iCE40UP5K, and LLM-based repair shows that simulation pass rates range from 3% to 88% across IRs but typically vary less than 1.25x across models within any single IR. On the resource-constrained iCE40, LLM designs achieve a higher conditional FPGA pass rate than reference solutions, 86.5% vs. 68.7%, not because they are better but because a simplicity bias makes them small enough to fit. The analysis reveals an accessibility-competence paradox: the most user-friendly IRs yield the worst LLM performance, suggesting that optimal IR selection will evolve as LLM capabilities grow.

Prithwish Basu Roy, Zeng Wang, Anatolii Chuvashlov et al.

Large Language Models (LLMs) have shown significant improvement in RTL code generation. Despite the advances, the generated code is often riddled with common vulnerabilities and weaknesses (CWEs) that can slip by untrained eyes. Attackers can often exploit these weaknesses to fulfill their nefarious motives. Existing RTL bug-detection techniques rely on rule-based checks, formal properties, or coarse-grained structural analysis, which either fail to capture semantic vulnerabilities or lack precise localization. In our work, we bridge this gap by proposing an embedding-based bug-detection framework that detects and classifies bugs at both module and line-level granularity. Our method achieves about 89% precision in identifying common CWEs such as CWE-1244 and CWE-1245, and 96% accuracy in detecting line-level bugs.

Weimin Fu, Zeng Wang, Minghao Shao et al.

RTL generation demands more than software code synthesis: designs must be syntactically valid, synthesizable, functionally correct, and hardware-efficient. Existing evaluations stop at functional correctness, leaving synthesizability and implementation quality unmeasured. We evaluate 32 language models on 202 Verilog tasks from VerilogEval and RTLLM, with five attempts each, scoring via the Hardware Quality Index (HQI), a 0--100 metric integrating post-synthesis area, delay, and warning count relative to expert references under a Nangate45 45\,nm flow. Three performance tiers emerge: 13 frontier models achieve Global HQI above 71, led by Gemini-3-Pro (87.5\% coverage, 85.1 HQI); 11 mid-tier models cluster at 53--68; 8 fall below 53. The capability-to-deployment gap (best-of-five vs.\ single-attempt) spans 3.8--22.1 HQI points, motivating multi-sample strategies. A tool-adjudicated taxonomy of 195 genuine synthesis failures reveals systematic divergence: proprietary models fail late through elaboration errors and synthesis timeout; open-weight models fail early through missing module wrappers and non-synthesizable constructs, consistent with training on simulation-grade rather than synthesis-grade RTL. Rankings hold across three technology libraries at Spearman~$ρ> 0.99$.

Saideep Sreekumar, Zeng Wang, Akashdeep Saha et al.

Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce TrojanGYM, an agentic, LLM-driven framework that automatically curates HT insertions to expose detector blind spots while preserving design correctness. Given high-level HT specifications, a suite of cooperating LLM agents (instantiated with GPT-4, LLaMA-3.3-70B, and Gemini-2.5Pro) proposes and refines RTL modifications that realize diverse triggers and payloads without impacting normal functionality. TrojanGYM implements a feedback-driven benchmark generation loop co-designed with HT detectors, in which constraint-aware syntactic checking and GNN-based HT detectors provide feedback that iteratively refines HT specifications and insertion strategies to better surface detector blind spots. We further propose Robust-GNN4TJ, a new implementation of the GNN4TJ with improved graph extraction, training robustness, and prediction reliability, especially on LLM-generated HT designs. On the most challenging TrojanGYM-generated benchmarks, Robust-GNN4TJ raises HT detection rates from 0% to 60% relative to a prior GNN-based detector. We instantiate TrojanGYM on SRAM, AES-128, and UART designs at RTL level, and show that it systematically produces diverse, functionally correct HTs that reach up to 83.33% evasion rates against modern GNN-based detectors, revealing robustness gaps that are not apparent when these detectors are evaluated solely on existing TrustHub-style benchmarks. Post peer-review, we will release all codes and artifacts.

Zeng Wang, Minghao Shao, Jitendra Bhandari et al.

Large Language Models (LLMs) have revolutionized code generation, achieving exceptional results on various established benchmarking frameworks. However, concerns about data contamination - where benchmark data inadvertently leaks into pre-training or fine-tuning datasets - raise questions about the validity of these evaluations. While this issue is known, limiting the industrial adoption of LLM-driven software engineering, hardware coding has received little to no attention regarding these risks. For the first time, we analyze state-of-the-art (SOTA) evaluation frameworks for Verilog code generation (VerilogEval and RTLLM), using established methods for contamination detection (CCD and Min-K% Prob). We cover SOTA commercial and open-source LLMs (CodeGen2.5, Minitron 4b, Mistral 7b, phi-4 mini, LLaMA-{1,2,3.1}, GPT-{2,3.5,4o}, Deepseek-Coder, and CodeQwen 1.5), in baseline and fine-tuned models (RTLCoder and Verigen). Our study confirms that data contamination is a critical concern. We explore mitigations and the resulting trade-offs for code quality vs fairness (i.e., reducing contamination toward unbiased benchmarking).

Zeng Wang, Lilas Alrahis, Likhitha Mankali et al.

Chip design is about to be revolutionized by the integration of large language, multimodal, and circuit models (collectively LxMs). While exploring this exciting frontier with tremendous potential, the community must also carefully consider the related security risks and the need for building trust into using LxMs for chip design. First, we review the recent surge of using LxMs for chip design in general. We cover state-of-the-art works for the automation of hardware description language code generation and for scripting and guidance of essential but cumbersome tasks for electronic design automation tools, e.g., design-space exploration, tuning, or designer training. Second, we raise and provide initial answers to novel research questions on critical issues for security and trustworthiness of LxM-powered chip design from both the attack and defense perspectives.

Zeng Wang, Minghao Shao, Mohammed Nabeel et al.

Large language models (LLMs) offer significant potential for coding, yet fine-tuning (FT) with curated data is essential for niche languages like Verilog. Using proprietary intellectual property (IP) for FT presents a serious risk, as FT data can be leaked through LLM inference. This leads to a critical dilemma for design houses: seeking to build externally accessible LLMs offering competitive Verilog coding, how can they leverage in-house IP to enhance FT utility while ensuring IP protection? For the first time in the literature, we study this dilemma. Using LLaMA 3.1-8B, we conduct in-house FT on a baseline Verilog dataset (RTLCoder) supplemented with our own in-house IP, which is validated through multiple tape-outs. To rigorously assess IP leakage, we quantify structural similarity (AST/Dolos) and functional equivalence (Synopsys Formality) between generated codes and our in-house IP. We show that our IP can indeed be leaked, confirming the threat. As defense, we evaluate logic locking of Verilog codes (ASSURE). This offers some level of protection, yet reduces the IP's utility for FT and degrades the LLM's performance. Our study shows the need for novel strategies that are both effective and minimally disruptive to FT, an essential effort for enabling design houses to fully utilize their proprietary IP toward LLM-driven Verilog coding.

Zeng Wang, Minghao Shao, Rupesh Karn et al.

Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.

Zeng Wang, Weihua Xiao, Minghao Shao et al.

Large Language Models (LLMs) show strong performance in RTL generation, but different models excel on different tasks because of architecture and training differences. Prior work mainly prompts or finetunes a single model. What remains not well studied is how to coordinate multiple different LLMs so they jointly improve RTL quality while also reducing cost, instead of running all models and choosing the best output. We define this as the multi-LLM RTL generation problem. We propose VeriDispatcher, a multi-LLM RTL generation framework that dispatches each RTL task to suitable LLMs based on pre-inference difficulty prediction. For each model, we train a compact classifier over semantic embeddings of task descriptions, using difficulty scores derived from benchmark variants that combine syntax, structural similarity, and functional correctness. At inference, VeriDispatcher uses these predictors to route tasks to a selected subset of LLMs. Across 10 diverse LLMs on RTLLM and VerilogEval, VeriDispatcher achieves up to 18% accuracy improvement on RTLLM using only 40% of commercial calls, and on VerilogEval maintains accuracy while reducing commercial usage by 25%, enabling cost-effective, high-quality LLM deployment in hardware design automation.

Zeng Wang, Minghao Shao, Akashdeep Saha et al.

Graph neural networks (GNNs) have shown promise in hardware security by learning structural motifs from netlist graphs. However, this reliance on motifs makes GNNs vulnerable to adversarial netlist rewrites; even small-scale edits can mislead GNN predictions. Existing adversarial approaches, ranging from synthesis-recipe perturbations to gate transformations, come with high design overheads. We present NetDeTox, an automated end-to-end framework that orchestrates large language models (LLMs) with reinforcement learning (RL) in a systematic manner, enabling focused local rewriting. The RL agent identifies netlist components critical for GNN-based reasoning, while the LLM devises rewriting plans to diversify motifs that preserve functionality. Iterative feedback between the RL and LLM stages refines adversarial rewritings to limit overheads. Compared to the SOTA work AttackGNN, NetDeTox successfully degrades the effectiveness of all security schemes with fewer rewrites and substantially lower area overheads (reductions of 54.50% for GNN-RE, 25.44% for GNN4IP, and 41.04% for OMLA, respectively). For GNN4IP, ours can even optimize/reduce the original benchmarks' area, in particular for larger circuits, demonstrating the practicality and scalability of NetDeTox.