Competition-level code generation with alphacode

Y Li, D Choi, J Chung, N Kushman, J Schrittwieser… - Science, 2022 - science.org
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …

Android source code vulnerability detection: a systematic literature review

J Senanayake, H Kalutarage, MO Al-Kadri… - ACM Computing …, 2023 - dl.acm.org
The use of mobile devices is rising daily in this technological era. A continuous and
increasing number of mobile applications are constantly offered on mobile marketplaces to …

Graph neural networks: foundation, frontiers and applications

L Wu, P Cui, J Pei, L Zhao, X Guo - … of the 28th ACM SIGKDD Conference …, 2022 - dl.acm.org
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Test smell detection tools: A systematic map** study

W Aljedaani, A Peruma, A Aljohani, M Alotaibi… - Proceedings of the 25th …, 2021 - dl.acm.org
Test smells are defined as sub-optimal design choices developers make when
implementing test cases. Hence, similar to code smells, the research community has …

Unsupervised translation of programming languages

B Roziere, MA Lachaux… - Advances in neural …, 2020 - proceedings.neurips.cc
A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …

Data quality for software vulnerability datasets

R Croft, MA Babar, MM Kholoosi - 2023 IEEE/ACM 45th …, 2023 - ieeexplore.ieee.org
The use of learning-based techniques to achieve automated software vulnerability detection
has been of longstanding interest within the software security domain. These data-driven …

DOBF: A deobfuscation pre-training objective for programming languages

MA Lachaux, B Roziere… - Advances in Neural …, 2021 - proceedings.neurips.cc
Recent advances in self-supervised learning have dramatically improved the state of the art
on a wide variety of tasks. However, research in language model pre-training has mostly …

A systematic literature review on source code similarity measurement and clone detection: Techniques, applications, and challenges

M Zakeri-Nasrabadi, S Parsa, M Ramezani… - Journal of Systems and …, 2023 - Elsevier
Measuring and evaluating source code similarity is a fundamental software engineering
activity that embraces a broad range of applications, including but not limited to code …

Breaking the silence: the threats of using llms in software engineering

J Sallou, T Durieux, A Panichella - Proceedings of the 2024 ACM/IEEE …, 2024 - dl.acm.org
Large Language Models (LLMs) have gained considerable traction within the Software
Engineering (SE) community, impacting various SE tasks from code completion to test …

Dobf: A deobfuscation pre-training objective for programming languages

B Roziere, MA Lachaux, M Szafraniec… - arxiv preprint arxiv …, 2021 - arxiv.org
Recent advances in self-supervised learning have dramatically improved the state of the art
on a wide variety of tasks. However, research in language model pre-training has mostly …