2 citations · 6 across the 35 of their papers we have counts for
38 papers
Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation
Guang Yang, Xing Hu, Xiang Chen +1
Large Language Models (LLMs) generate register-transfer-level (RTL) code with rapidly improving functional correctness. Security of LLM-generated code, however, has been studied ma…
Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation
Guang Yang, Xing Hu, Xiang Chen +2
Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, yet their performance degrades significantly on low-resource Hardware Description Languag…
Automating Just-In-Time Python Type Annotation Updating
Zhipeng Xue, Zhipeng Gao, Xing Hu +3
Type annotations are more and more popular in Python projects to avoid type errors caused by Python's dynamic typing feature. However, when developers change source code, these typ…
Refploit: Facilitating Exploit Construction via Code-Agent Trajectory Repair
Zirui Chen, Zhipeng Xue, Jiayuan Zhou +3
Vulnerability exploits play a crucial role in assessing the downstream impact of Java library vulnerabilities. While some vulnerabilities are accompanied by disclosed exploit refer…
IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test Migration
Yi Gao, Ziyuan Zhang, Xing Hu +2
Unit tests capture both functional checks and domain-specific knowledge, but this knowledge remains locked within individual projects and is rarely reused across libraries with ove…
ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis
Xinwei Mao, Zirui Chen, Xing Hu +1
Exploits are widely used to check whether library vulnerabilities appear in different versions and to mark affected version ranges. Exploit-based checks sometimes fail because expl…
On the Shoulders of Giants: Empowering Automated Smart Contract Auditing via the GiAnt Corpus
Xiaoting Zhang, Zhipeng Gao, Yiran Lv +3
High-quality smart contract auditing datasets are crucial for evaluating security tools and advancing smart contract security research. Two major limitations of existing datasets a…
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
Xiao Li, Xiang Zheng, Yifeng Gao +35
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As…
Exploiting LLM Agent Supply Chains via Payload-less Skills
Xinyu Liu, Yukai Zhao, Xing Hu +1
Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations br…
From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation
Guang Yang, Xing Hu, Xiang Chen +1
Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit…
Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing
Yukai Zhao, Menghan Wu, Xing Hu +3
Developers utilize third-party libraries to improve productivity, which also introduces potential security risks. Existing approaches generate tests for public functions to trigger…
Mitigating Implicit Inconsistencies in Patch Porting
Shengyi Pan, Zhongxin Liu, Jiayuan Zhou +3
Promptly porting patches from a source codebase to its variants (e.g., forks and branches) is essential for mitigating propagated defects and vulnerabilities. Recent studies have e…
An Empirical Study of Speculative Decoding on Software Engineering Tasks
Yijia Li, Junkai Chen, Xing Hu +1
Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. Howeve…
When Models Meet Users: An Empirical Study of Perceptions of General LLMs and Multimodal LLMs on Hugging Face
Yujian Liu, Xiao Yu, Jacky Keung +3
Large language models (LLMs) have rapidly evolved from general-purpose systems to multimodal models capable of processing text, images, and audio. As both general-purpose LLMs (GLL…
Verify Implementation Equivalence of Large Models
Qi Zhan, Xing Hu, Xin Xia +1
Verifying whether two implementations of the same large model are equivalent across frameworks is difficult in practice. Even when they realize the same computation, their graphs m…
RACE-Bench: A Reasoning-Augmented Benchmark for Repository-Level Code Agents on Feature Addition
Shuhan Liu, Zhiyi Zhao, Xing Hu +3
Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, exist…
Assessing the Cross-Version Applicability of Java Library Vulnerability Exploits
Zirui Chen, Qi Zhan, Jiayuan Zhou +3
Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulne…
Every Maintenance Has Its Exemplar: The Future of Software Maintenance through Migration
Zirui Chen, Xing Hu, Xin Xia +1
Maintenance is a critical stage in the software lifecycle, ensuring that post-release systems remain reliable, efficient, and adaptable. However, manual software maintenance is lab…
Forecasting Developer Environments with GenAI: A Research Perspective
Raula Gaikovina Kula, Christoph Treude, Xing Hu +28
Generative Artificial Intelligence (GenAI) models are achieving remarkable performance in various tasks, including code generation, testing, code review, and program repair. The ab…
Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
Guang Yang, Xing Hu, Xiang Chen +1
Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where adversaries inject malicious t…
DepRadar: Agentic Coordination for Context Aware Defect Impact Analysis in Deep Learning Libraries
Yi Gao, Xing Hu, Tongtong Xu +3
Deep learning libraries like Transformers and Megatron are now widely adopted in modern AI programs. However, when these libraries introduce defects, ranging from silent computatio…
Actionable Warning Is Not Enough: Recommending Valid Actionable Warnings with Weak Supervision
Zhipeng Xue, Zhipeng Gao, Tongtong Xu +3
The use of static analysis tools has gained increasing popularity among developers in the last few years. However, the widespread adoption of static analysis tools is hindered by t…
Don't Use a Cannon to Kill a Fly: Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations
Guancheng Lin, Xiao Yu, Jacky Keung +3
Pre-trained or fine-tuned on large code corpora, Large Language Models (LLMs) have demonstrated strong performance in code completion tasks. However, their embedded knowledge is co…
Diffploit: Facilitating Cross-Version Exploit Migration for Open Source Library Vulnerabilities
Zirui Chen, Zhipeng Xue, Jiayuan Zhou +3
Exploits are commonly used to demonstrate the presence of library vulnerabilities and validate their impact across different versions. However, their direct application to alternat…