Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Minghao Shao

Minghao Shao

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Crypto×2Architecture×1ML×1Prog. Lang.×1Multiagent×1

Frequent co-authors

Muhammad Shafique3×
Boyuan Chen2×
Yijun Shen1×
Yichen Zhao1×
Zhuoyan Yu1×
Yik-Cheung Tam1×

Research Timeline

2026
HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking

The paper introduces HarmChip, a novel benchmark to evaluate LLM vulnerability to domain-specific hardware security threats, revealing that current safety guardrails fail against semantically disguised attacks.

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports for vulnerable code.

VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation

The paper introduces VHDLSuite, an infrastructure for evaluating Large Language Models in VHDL, including a data pipeline, benchmark, and evaluation framework.

Highlighted terms show continued research focus across papers

Papers

cs.ARcs.AIcs.LGEmpiricalRecentJun 11, 2026

VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation

Yijun Shen, Minghao Shao, Yichen Zhao, Zhuoyan Yu +3 more

The paper introduces VHDLSuite, an infrastructure for evaluating Large Language Models in VHDL, including a data pipeline, benchmark, and evaluation framework.

View →
cs.CRcs.AIcs.MARecent
Apr 20, 2026

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs

Parteek Jamwal, Minghao Shao, Boyuan Chen, Achyuta Muthuvelan +14 more

The paper introduces RAVEN, a Retrieval-Augmented Vulnerability Exploration Network, which uses LLM agents and RAG to automatically generate comprehensive, structured vulnerability analysis reports fo…

View →
cs.CRRecentApr 18, 2026

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking

Zeng Wang, Minghao Shao, Weimin Fu, Prithwish Basu Roy +5 more

The paper introduces HarmChip, a novel benchmark to evaluate LLM vulnerability to domain-specific hardware security threats, revealing that current safety guardrails fail against semantically disguise…

View →