activity
20242026
most citedHarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking

1 citations · 1 across the 20 of their papers we have counts for

collaborators
Showing 2025Show all

11 papers · 1 filter

cs.CR2025

Revisiting Logic Encryption

Rupesh Raj Karn, Lakshmi Likhitha Mankali, Zeng Wang +5

Modern circuits face various threats like reverse engineering, theft of intellectual property (IP), side-channel attacks, etc. Here, we present a novel approach for IP protection b…

cs.CR2025

TrojanLoC: LLM-based Framework for RTL Trojan Localization

Weihua Xiao, Zeng Wang, Minghao Shao +6

Hardware Trojans (HT s) are a persistent threat to integrated circuits, especially when inserted at the register-transfer level (RTL). Existing methods typically first convert the…

cs.CR2025

LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs

Akashdeep Saha, Zeng Wang, Prithwish Basu Roy +3

Despite rapid progress in logic locking (LL), reproducibility remains a challenge as codes are rarely made public. We present LockForge, a first-of-its-kind, multi-agent large lang…

cs.CR2025

NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration

Zeng Wang, Minghao Shao, Akashdeep Saha +4

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 ad…

cs.LG2025

VeriDispatcher: Multi-Model Dispatching through Pre-Inference Difficulty Prediction for RTL Generation Optimization

Zeng Wang, Weihua Xiao, Minghao Shao +4

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 m…

cs.LG2025

SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design

Zeng Wang, Minghao Shao, Rupesh Karn +6

Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data sec…