84 citations · 99 across the 34 of their papers we have counts for
36 papers
Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks
Boyuan Chen, Yehia Dawoud, Hailemariam Mersha +4
Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313…
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio
Boyuan Chen, Minseok Kim, Sohaila Abdulsattar +4
We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-tim…
How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation
Kimberly Milner, Minghao Shao, Nanda Rani +8
Capture-the-Flag (CTF) benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or…
FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?
Weimin Fu, Hejia Zhang, Minghao Shao +6
Can large language models generate not just correct, but fast hardware? This paper investigates the question in financial FPGA design, where 5-10 nanoseconds of latency determines…
VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation
Yijun Shen, Minghao Shao, Yichen Zhao +4
Large Language Models (LLM) have shown impressive capabilities in Register Transfer Level (RTL) code generation, particularly for Verilog. However, evaluating their performance wit…
QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy
Pasindu Wickramasinghe, Achyuta Muthuvelan, Rachmad Vidya Wicaksana Putra +2
LLMs have become the state-of-the-art algorithms for solving NLP tasks. However, they typically come at huge computational and memory costs, thus making them difficult to deploy on…
Exposing and Mitigating Temporal Attack in Deepfake Video Detection
Zheyuan Gu, Minghao Shao, Zhen Wang +4
While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum…
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
Minghao Shao, Nouhaila Innan, Hariharan Janardhanan +3
The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistants: general-purpose models hall…
Code for All: Educational Applications of the "Vibe Coding" Hackathon in Programming Education across All Skill Levels
Ashley J. Chen, Yijia Cao, Minghao Shao +2
The emergence of large language models has enabled vibe coding, a natural language approach to programming in which users describe intent and AI generates or revises code, potentia…
Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models
Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif +3
This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks w…
Configuration Over Selection: Hyperparameter Sensitivity Exceeds Model Differences in Open-Source LLMs for RTL Generation
Minghao Shao, Zeng Wang, Weimin Fu +5
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…
From Natural Language to Silicon: The Representation Bottleneck in LLM Hardware Design
Weimin Fu, Zeng Wang, Minghao Shao +5
Edge applications increasingly demand custom hardware, yet Field-Programmable Gate Array (FPGA) design requires expertise that domain engineers lack. Large Language Models (LLMs) p…
HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking
Zeng Wang, Minghao Shao, Weimin Fu +6
The integration of large language models (LLMs) into electronic design automation (EDA) workflows has introduced powerful capabilities for RTL generation, verification, and design…
RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs
Parteek Jamwal, Minghao Shao, Boyuan Chen +15
Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However,…
AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes
Haoran Xi, Minghao Shao, Kimberly Milner +11
Large language models are rapidly changing how learners acquire and demonstrate cybersecurity skills. However, when human--AI collaboration is allowed, educators still lack validat…
GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations
Boyuan Chen, Minghao Shao, Siddharth Garg +2
Vision Language Models (VLMs) exhibit persistent hallucinations in counting tasks, with accuracy substantially lower than other visual reasoning tasks (excluding sentiment). This p…
Synthesis-in-the-Loop Evaluation of LLMs for RTL Generation: Quality, Reliability, and Failure Modes
Weimin Fu, Zeng Wang, Minghao Shao +5
RTL generation is more than code synthesis. Designs must be syntactically valid, synthesizable, correct, hardware-efficient. SOTA evaluations stop at functional correctness and do…
CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking
Nanda Rani, Kimberly Milner, Minghao Shao +9
Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effect…
TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion
Saideep Sreekumar, Zeng Wang, Akashdeep Saha +6
Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce Troja…
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…
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…
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…
From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization
Haoran Xi, Minghao Shao, Brendan Dolan-Gavitt +2
Large language models show promise for vulnerability discovery, yet prevailing methods inspect code in isolation, struggle with long contexts, and focus on coarse function- or file…
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
Minghao Shao, Nanda Rani, Kimberly Milner +9
Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate t…