☆ 4.6 Article

How Important are Good Method Names in Neural Code Generation? A Model Robustness Perspective

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Software Engineering

Towards Robustness of Deep Program Processing Models-Detection, Estimation, and Enhancement

Huangzhao Zhang et al.

Summary: This article introduces a framework called CARROT for robustness detection, measurement, and enhancement of deep learning models for source code processing. The framework proposes attack techniques, robustness metrics, and adversarial training methods, and evaluates its effectiveness on various source code processing tasks.

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY (2022)

添加到收藏夹

Article Computer Science, Software Engineering

Adversarial Robustness of Deep Code Comment Generation

Yu Zhou et al.

Summary: This study focuses on the robustness issue of deep neural networks (DNNs) applied to code comment generation in software engineering. The paper proposes ACCENT, an identifier substitution approach, to craft adversarial code snippets that can mislead DNNs to produce irrelevant code comments. The study also includes a novel training method to improve the robustness of existing code comment generation models.

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CCGIR: Information retrieval-based code comment generation method for smart contracts

Guang Yang et al.

Summary: A proposed information retrieval-based code comment generation method, CCGIR, improves the efficiency and quality of code comments in smart contract development by reusing comments from similar code in the code repository. Experimental results show that CCGIR outperforms nine other baselines in terms of performance measures and a human study validates the generation of higher quality comments. Additionally, CCGIR shows promising performance in other code comment generation tasks.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Software Engineering

Can we generate shellcodes via natural language? An empirical study

Pietro Liguori et al.

Summary: This study proposes an approach based on Neural Machine Translation (NMT) to automatically generate shellcodes from natural language descriptions. They conducted an empirical study using a novel dataset and proposed new metrics for evaluating the accuracy of NMT in generating shellcodes.

AUTOMATED SOFTWARE ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Information Systems

On the generalizability of Neural Program Models with respect to semantic-preserving program transformations

Md Rafiqul Islam Rabin et al.

Summary: This paper proposes to evaluate the generalizability of neural program models by measuring their performance on semantic-preserving transformations. The results indicate that neural program models often struggle with small semantic changes in programs, but the generalizability of correct predictions can be improved with larger and more diverse training datasets.

INFORMATION AND SOFTWARE TECHNOLOGY (2021)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

EVIL: Exploiting Software via Natural Language

Pietro Liguori et al.

Summary: Proposing an approach, EVIL, to automatically generate exploits in assembly/Python language from descriptions in natural language, leveraging Neural Machine Translation (NMT) techniques and a developed dataset. Extensive experimental study showed high accuracy in terms of syntactic and semantic correctness in generating exploits.

2021 IEEE 32ND INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING (ISSRE 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

Lightweight Global and Local Contexts Guided Method Name Recommendation with Prior Knowledge

Shangwen Wang et al.

Summary: This study conducted a large-scale empirical analysis on method names and proposed a context-guided method name recommender that integrates local and global context information, as well as empirical results as prior knowledge. The recommender outperformed existing approaches on method name recommendation and consistency checking tasks, indicating the significant contributions of caller/callee information and prior knowledge to its overall performance.

PROCEEDINGS OF THE 29TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '21) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

RobOT: Robustness-Oriented Testing for Deep Learning Systems

Jingyi Wang et al.

Summary: The study introduces a novel testing framework called "Robustness-Oriented Testing (RobOT)" aimed at effectively improving the robustness of deep learning models. Through a new metric, test cases valuable for enhancing model robustness are automatically generated, demonstrating the effectiveness and efficiency of RobOT in improving model robustness.

2021 IEEE/ACM 43RD INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2021) (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Adversarial Examples for Models of Code

Noam Yefet et al.

PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL (2020)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

A Neural Model for Method Name Generation from Functional Description

Sa Gao et al.

2019 IEEE 26TH INTERNATIONAL CONFERENCE ON SOFTWARE ANALYSIS, EVOLUTION AND REENGINEERING (SANER) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

Method Name Suggestion with Hierarchical Attention Networks

Sihan Xu et al.

PROCEEDINGS OF THE 2019 ACM SIGPLAN WORKSHOP ON PARTIAL EVALUATION AND PROGRAM MANIPULATION (PEPM '19) (2019)

添加到收藏夹

Article Computer Science, Theory & Methods

A Survey of Machine Learning for Big Code and Naturalness

Miltiadis Allamanis et al.

ACM COMPUTING SURVEYS (2018)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow

Pengcheng Yin et al.

2018 IEEE/ACM 15TH INTERNATIONAL CONFERENCE ON MINING SOFTWARE REPOSITORIES (MSR) (2018)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Towards Evaluating the Robustness of Neural Networks

Nicholas Carlini et al.

2017 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP) (2017)

添加到收藏夹

Article Computer Science, Hardware & Architecture

On the Naturalness of Software

Abram Hindle et al.

COMMUNICATIONS OF THE ACM (2016)

添加到收藏夹

Article Computer Science, Software Engineering

How We Refactor, and How We Know It

Emerson Murphy-Hill et al.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2012)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An alternative approach for neural network evolution with a genetic algorithm:: Crossover by combinatorial optimization

Nicolas Garcia-Pedrajas et al.

NEURAL NETWORKS (2006)

添加到收藏夹

Article Computer Science, Information Systems

An information-theoretic perspective of tf-idf measures

A Aizawa

INFORMATION PROCESSING & MANAGEMENT (2003)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.