Search Results for author:
Found 64 papers, 28 papers with code
Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
Additionally, we show that role-specific instruction tuning in multi-agent with small data (50 pair samples) improves the performance of VulTrial further by 139. 89% and 118. 30%.
Zero-Shot Cross-Domain Code Search without Fine-Tuning
In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching.
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Through RLAIF, R2Vul enables LLMs to produce structured, security-aware reasoning that is actionable and reliable while explicitly learning to distinguish valid assessments from misleading ones.
Less is More: On the Importance of Data Quality for Unit Test Generation
To evaluate its effectiveness, we apply CleanTest on two widely-used test generation datasets, i. e., Methods2Test and Atlas.
Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learning
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information.
AiRacleX: Automated Detection of Price Oracle Manipulations via LLM-Driven Knowledge Mining and Prompt Generation
Decentralized finance (DeFi) applications depend on accurate price oracles to ensure secure transactions, yet these oracles are highly vulnerable to manipulation, enabling attackers to exploit smart contract vulnerabilities for unfair asset valuation and financial gain.
LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks
To address the data leakage, we introduce \textbf{LessLeak-Bench}, a new benchmark that removes leaked samples from the 83 SE benchmarks, enabling more reliable LLM evaluations in future research.
Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
We evaluate seven gender bias detectors and find that none fully capture the actual level of bias in T2I models, with some detectors overestimating bias by up to 26. 95%.
TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification
Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendations, and business analytics on e-commerce platforms.
Towards a Classification of Open-Source ML Models and Datasets for Software Engineering
Aims: We apply an SE-oriented classification to PTMs and datasets on a popular open-source ML repository, Hugging Face (HF), and analyze the evolution of PTMs over time.
How do Machine Learning Models Change?
While previous studies have examined aspects of models hosted on platforms like HF, a comprehensive longitudinal study of how these models change remains underexplored.
B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests
Our proposed approximated optimal strategy B4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios.
LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems
Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs.
Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection
There are two popular lines of work to address automated vulnerability detection.
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions.
Ranked #1 on
Code Generation
on BigCodeBench-Instruct
AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
To improve inference efficiency and reduce computational costs, we propose the concept of AI-oriented grammar.
Bridging Expert Knowledge with Deep Learning Techniques for Just-In-Time Defect Prediction
In addition, our experimental results confirm that the simple model and complex model are complementary to each other.
A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research
The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).
Inferring Properties of Graph Neural Networks
To tackle the challenge of varying input structures in GNNs, GNNInfer first identifies a set of representative influential structures that contribute significantly towards the prediction of a GNN.
Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education
This is achieved by generating code in response to a given question using different variants.
Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps
For decades, much software engineering research has been dedicated to devising automated solutions aimed at enhancing developer productivity and elevating software quality.
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models
In this paper, we deliver a comprehensive study of PEFT techniques for LLMs in the context of automated code generation.
Large Language Models for Software Engineering: A Systematic Literature Review
Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages.
Source Code Data Augmentation for Deep Learning: A Survey
This paper fills this gap by conducting a comprehensive and integrative survey of data augmentation for source code, wherein we systematically compile and encapsulate existing literature to provide a comprehensive overview of the field.
Multi-Granularity Detector for Vulnerability Fixes
To address these challenges and boost the effectiveness of prior works, we propose MiDas (Multi-Granularity Detector for Vulnerability Fixes).
On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code
We demonstrate that the most commonly used fine-tuning technique from prior work is not robust enough to handle the dynamic nature of APIs, leading to the loss of previously acquired knowledge i. e., catastrophic forgetting.
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code.
Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking
The increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern.
Regret-Based Defense in Adversarial Reinforcement Learning
We demonstrate that our approaches provide a significant improvement in performance across a wide variety of benchmarks against leading approaches for robust Deep RL.
ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems
To address these limitations, our tool incorporates two novel features: (1) a text transformation module to boost the number of generated test cases and uncover more errors in ASR systems and (2) a phonetic analysis module to identify on which phonemes the ASR system tend to produce errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning
In case our approach fails to determine an overfitting patch based on invariants, INVALIDATOR utilizes a trained model from labeled patches to assess patch correctness based on program syntax.
DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode
Central to applying ML to software artifacts (like source or executable code) is converting them into forms suitable for learning.
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack.
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
To fill this significant gap, we first investigate the prompts of unhelpful code completions, called "low-return prompts".
AutoPruner: Transformer-Based Call Graph Pruning
Given a call graph constructed by traditional static analysis tools, AutoPruner takes a Transformer-based approach to capture the semantic relationships between the caller and callee functions associated with each edge in the call graph.
VulCurator: A Vulnerability-Fixing Commit Detector
Open-source software (OSS) vulnerability management process is important nowadays, as the number of discovered OSS vulnerabilities is increasing over time.
How to Find Actionable Static Analysis Warnings: A Case Study with FindBugs
Automatically generated static code warnings suffer from a large number of false alarms.
An Exploratory Study on Code Attention in BERT
When identifiers' embeddings are used in CodeBERT, a code-based PLM, the performance is improved by 21-24% in the F1-score of clone detection.
On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages
Furthermore, some programming languages are inherently different and code written in one language usually cannot be interchanged with the others, i. e., Ruby and Java code possess very different structure.
On the Effectiveness of Pretrained Models for API Learning
We have also identified two different tokenization approaches that can contribute to a significant boost in PTMs' performance for the API sequence generation task.
Code Smells in Machine Learning Systems
We found that our newly identified code smells are prevalent and impactful on the maintenance of DL systems from the developer's perspective.
FACOS: Finding API Relevant Contents on Stack Overflow with Semantic and Syntactic Analysis
Leveraging this observation, we develop FACOS, a context-specific algorithm to capture the semantic and syntactic information of the paragraphs and code snippets in a discussion.
Smart Contract Security: a Practitioners' Perspective
Given numerous research efforts in addressing the security issues of smart contracts, we wondered how software practitioners build security into smart contracts in practice.
Software Engineering
AndroEvolve: Automated Update for Android Deprecated-API Usages
Usages of deprecated APIs in Android apps need to be updated to ensure the apps' compatibility with the old and new versions of Android OS.
Software Engineering
Characterization and Automatic Update of Deprecated Machine-Learning API Usages
In this paper, we built a tool to automate these updates.
Software Engineering
What Makes a Popular Academic AI Repository?
Hence, in this study, we perform an empirical study on academic AI repositories to highlight good software engineering practices of popular academic AI repositories for AI researchers.
Software Engineering
Emerging App Issue Identification via Online Joint Sentiment-Topic Tracing
Experiments on popular apps from Google Play and Apple's App Store demonstrate the effectiveness of MERIT in identifying emerging app issues, improving the state-of-the-art method by 22. 3% in terms of F1-score.
On the Replicability and Reproducibility of Deep Learning in Software Engineering
Experimental results show the importance of replicability and reproducibility, where the reported performance of a DL model could not be replicated for an unstable optimization process.
CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words
CodeMatcher first collects metadata for query words to identify irrelevant/noisy ones, then iteratively performs fuzzy search with important query words on the codebase that is indexed by the Elasticsearch tool, and finally reranks a set of returned candidate code according to how the tokens in the candidate code snippet sequentially matched the important words in a query.
Generating Question Titles for Stack Overflow from Mined Code Snippets
Stack Overflow has been heavily used by software developers as a popular way to seek programming-related information from peers via the internet.
Software Engineering
Keen2Act: Activity Recommendation in Online Social Collaborative Platforms
The Act step then recommends to the user which activities to perform on the identified set of items.
Automating App Review Response Generation
Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app.
Checking Smart Contracts with Structural Code Embedding
However, many bugs and vulnerabilities have been identified in many contracts which raises serious concerns about smart contract security, not to mention that the blockchain systems on which the smart contracts are built can be buggy.
Software Engineering
Smart Contract Repair
Our approach can be used to optimise the overall security and reliability of smart contracts against malicious attackers.
Software Engineering Cryptography and Security 68N15 D.1.2
TreeCaps: Tree-Structured Capsule Networks for Program Source Code Processing
Program comprehension is a fundamental task in software development and maintenance processes.
Automatic Generation of Pull Request Descriptions
We build a dataset with over 41K PRs and evaluate our approach on this dataset through ROUGE and a human evaluation.
Software Engineering
SmartEmbed: A Tool for Clone and Bug Detection in Smart Contracts through Structural Code Embedding
In addition to the uses by individual developers, SmartEmbed can also be applied to studies of smart contracts in a large scale.
Software Engineering
Question Relatedness on Stack Overflow: The Task, Dataset, and Corpus-inspired Models
The proposed dataset Stack Overflow is a useful resource to develop novel solutions, specifically data-hungry neural network models, for the prediction of relatedness in technical community question-answering forums.
PatchNet: A Tool for Deep Patch Classification
This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes.
Network-Clustered Multi-Modal Bug Localization
To help the developers debug, numerous information retrieval (IR)-based and spectrum-based bug localization techniques have been devised.
WebAPIRec: Recommending Web APIs to Software Projects via Personalized Ranking
In this light, we propose a new, automated approach called WebAPIRec that takes as input a project profile and outputs a ranked list of {web} APIs that can be used to implement the project.
Collective Semi-Supervised Learning for User Profiling in Social Media
The abundance of user-generated data in social media has incentivized the development of methods to infer the latent attributes of users, which are crucially useful for personalization, advertising and recommendation.
Watch out for This Commit! A Study of Influential Software Changes
One single code change can significantly influence a wide range of software systems and their users.
Software Engineering
Duplicate Bug Report Detection With a Combination of Information Retrieval and Topic Modeling
Detecting duplicate bug reports helps reduce triaging efforts and save time for developers in fixing the same issues.
