Source Code
Source code, the fundamental building block of software, is the subject of intense research focusing on improving its analysis, generation, and security. Current efforts leverage machine learning, particularly transformer-based models like BERT and GPT variants, and graph neural networks, to analyze code for vulnerabilities, predict defects, and even automatically generate code from natural language descriptions. These advancements have significant implications for software development, enhancing code quality, security, and developer productivity, while also raising new challenges related to code authorship attribution and the detection of AI-generated code.
Papers
An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code
Max Hort, Anastasiia Grishina, Leon Moonen
The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification
Norbert Tihanyi, Tamas Bisztray, Ridhi Jain, Mohamed Amine Ferrag, Lucas C. Cordeiro, Vasileios Mavroeidis
Analysis of ChatGPT on Source Code
Ahmed R. Sadik, Antonello Ceravola, Frank Joublin, Jibesh Patra
Feature Engineering-Based Detection of Buffer Overflow Vulnerability in Source Code Using Neural Networks
Mst Shapna Akter, Hossain Shahriar, Juan Rodriguez Cardenas, Sheikh Iqbal Ahamed, Alfredo Cuzzocrea
Task-aware Distributed Source Coding under Dynamic Bandwidth
Po-han Li, Sravan Kumar Ankireddy, Ruihan Zhao, Hossein Nourkhiz Mahjoub, Ehsan Moradi-Pari, Ufuk Topcu, Sandeep Chinchali, Hyeji Kim
Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering
Davit Soselia, Khalid Saifullah, Tianyi Zhou