121 citations · 173 across the 25 of their papers we have counts for
29 papers
Taylor-Approximation-Based Repair of High Floating-Point Errors
Xin Yi, Liqian Chen, Hengbiao Yu +5
Numerical libraries can still lose many bits of accuracy on localized ill-conditioned inputs, such as roots, poles, cancellation points, and branch boundaries. This paper presents…
Behavior Specification-Guided Program Synthesis for Binary Deobfuscation
Kangchen Zhu, Shangwen Wang, Zhiliang Tian +5
Deobfuscation is critical to reverse engineering and security analysis because it restores the readability and analyzability of obfuscated code. However, existing research primaril…
Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
Xin Peng, Bo Lin, Jing Wang +5
Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-int…
Atomizer: An LLM-based Collaborative Multi-Agent Framework for Intent-Driven Commit Untangling
Kangchen Zhu, Zhiliang Tian, Shangwen Wang +2
Composite commits, which entangle multiple unrelated concerns, are prevalent in software development and significantly hinder program comprehension and maintenance. Existing automa…
Exploring the Security Threats of Retriever Backdoors in Retrieval-Augmented Code Generation
Tian Li, Bo Lin, Shangwen Wang +1
Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security implications remain dangerously under…
Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
Bo Lin, Shangwen Wang, Yihao Qin +2
Retrieval-Augmented Code Generation (RACG) leverages external knowledge to enhance Large Language Models (LLMs) in code synthesis, improving the functional correctness of the gener…
Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
Sheng Ouyang, Yihao Qin, Bo Lin +3
The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development ef…
Large Language Models-Aided Program Debloating
Bo Lin, Shangwen Wang, Yihao Qin +2
As software grows in complexity to accommodate diverse features and platforms, software bloating has emerged as a significant challenge, adversely affecting performance and securit…
Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation
Bo Lin, Shangwen Wang, Liqian Chen +1
The integration of Large Language Models (LLMs) into software development has revolutionized the field, particularly through the use of Retrieval-Augmented Code Generation (RACG) s…
Keep It Simple: Towards Accurate Vulnerability Detection for Large Code Graphs
Xin Peng, Shangwen Wang, Yihao Qin +3
Software vulnerability detection is crucial for high-quality software development. Recently, some studies utilizing Graph Neural Networks (GNNs) to learn the graph representation o…
There are More Fish in the Sea: Automated Vulnerability Repair via Binary Templates
Bo Lin, Shangwen Wang, Liqian Chen +1
As software vulnerabilities increase in both volume and complexity, vendors often struggle to repair them promptly. Automated vulnerability repair has emerged as a promising soluti…
Fault Localization from the Semantic Code Search Perspective
Yihao Qin, Shangwen Wang, Yan Lei +5
The software development process is characterized by an iterative cycle of continuous functionality implementation and debugging, essential for the enhancement of software quality…
Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering
Tanghaoran Zhang, Yue Yu, Xinjun Mao +5
Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires deve…
AgentFL: Scaling LLM-based Fault Localization to Project-Level Context
Yihao Qin, Shangwen Wang, Yiling Lou +4
Fault Localization (FL) is an essential step during the debugging process. With the strong capabilities of code comprehension, the recent Large Language Models (LLMs) have demonstr…
When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
Zhensu Sun, Xiaoning Du, Fu Song +2
Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However…
Enhancing Code Intelligence Tasks with ChatGPT
Kang Yang, Xinjun Mao, Shangwen Wang +6
Pre-trained code models have emerged as crucial tools in various code intelligence tasks. However, their effectiveness depends on the quality of the pre-training dataset, particula…
An Extensive Study on Adversarial Attack against Pre-trained Models of Code
Xiaohu Du, Ming Wen, Zichao Wei +2
Transformer-based pre-trained models of code (PTMC) have been widely utilized and have achieved state-of-the-art performance in many mission-critical applications. However, they ca…
FITNESS: A Causal De-correlation Approach for Mitigating Bias in Machine Learning Software
Ying Xiao, Shangwen Wang, Sicen Liu +3
Software built on top of machine learning algorithms is becoming increasingly prevalent in a variety of fields, including college admissions, healthcare, insurance, and justice. Th…
CCT5: A Code-Change-Oriented Pre-Trained Model
Bo Lin, Shangwen Wang, Zhongxin Liu +3
Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or id…
Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning
Mingyang Geng, Shangwen Wang, Dezun Dong +5
Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a…
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
Zhensu Sun, Xiaoning Du, Fu Song +4
Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, aro…
Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness
Haoye Tian, Xunzhu Tang, Andrew Habib +5
In this work, we propose a novel perspective to the problem of patch correctness assessment: a correct patch implements changes that "answer" to a problem posed by buggy behaviour.…
Beep: Fine-grained Fix Localization by Learning to Predict Buggy Code Elements
Shangwen Wang, Kui Liu, Bo Lin +4
Software Fault Localization refers to the activity of finding code elements (e.g., statements) that are related to a software failure. The state-of-the-art fault localization techn…
A Fine-grained Data Set and Analysis of Tangling in Bug Fixing Commits
Steffen Herbold, Alexander Trautsch, Benjamin Ledel +45
Context: Tangled commits are changes to software that address multiple concerns at once. For researchers interested in bugs, tangled commits mean that they actually study not only…