ASE 2023
Mon 11 - Fri 15 September 2023 Kirchberg, Luxembourg
Wed 13 Sep 2023 14:18 - 14:30 at Plenary Room 2 - Code Summarization Chair(s): Ray Buse

Decompilation is a widely used process for reverse engineers to significantly enhance code readability by lifting assembly code to a higher-level C-like language, pseudo-code. Nevertheless, the process of compilation and stripping irreversibly discards high-level semantic information that is crucial to code comprehension, such as comments, identifier names, and types. Existing approaches typically recover only one type of information, making them suboptimal for semantic inference. In this paper, we treat pseudo-code as a special programming language, then present a unified pre-trained model, HexT5, that is trained on vast amounts of natural language comments, source identifiers, and pseudo-code using novel pseudo-code-based pretraining objectives. We fine-tune HexT5 on various downstream tasks, including code summarization, variable name recovery, function name recovery, and similarity detection. Comprehensive experiments show that HexT5 achieves state-of-the-art performance on four downstream tasks, and it demonstrates the robust effectiveness and generalizability of HexT5 for binary-related tasks.

[paper] HexT5: Unified Pre-training for Stripped Binary Code Information Inference (HexT5_ASE_2023.pdf)1.4MiB
[slides] HexT5: Unified Pre-training for Stripped Binary Code Information Inference (HexT5-ASE2023-slides.pdf)1.14MiB

Wed 13 Sep

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

13:30 - 15:00
Code SummarizationResearch Papers at Plenary Room 2
Chair(s): Ray Buse Google
13:30
12m
Talk
Delving into Commit-Issue Correlation to Enhance Commit Message Generation Models
Research Papers
Liran Wang Beihang University, Xunzhu Tang University of Luxembourg, Yichen He Beihang University, Changyu Ren Beihang University, Shuhua Shi Beihang University, Chaoran Yan Beihang University, Zhoujun Li Beihang University
Pre-print File Attached
13:42
12m
Talk
From Commit Message Generation to History-Aware Commit Message Completion
Research Papers
Aleksandra Eliseeva JetBrains Research, Yaroslav Sokolov JetBrains, Egor Bogomolov JetBrains Research, Yaroslav Golubev JetBrains Research, Danny Dig JetBrains Research & University of Colorado Boulder, USA, Timofey Bryksin JetBrains Research
Pre-print File Attached
13:54
12m
Talk
Automatic Generation and Reuse of Precise Library Summaries for Object-Sensitive Pointer Analysis
Research Papers
Jingbo Lu University of New South Wales, Dongjie He UNSW, Wei Li University of New South Wales, Yaoqing Gao Huawei Toronto Research Center, Jingling Xue UNSW
Pre-print File Attached
14:06
12m
Talk
What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
Research Papers
Shuzheng Gao The Chinese University of Hong Kong, Xin-Cheng Wen Harbin Institute of Technology, Cuiyun Gao Harbin Institute of Technology, Wenxuan Wang Chinese University of Hong Kong, Hongyu Zhang Chongqing University, Michael Lyu The Chinese University of Hong Kong
Pre-print File Attached
14:18
12m
Talk
HexT5: Unified Pre-training for Stripped Binary Code Information InferenceRecorded talk
Research Papers
Jiaqi Xiong University of Science and Technology of China, Guoqiang Chen University of Science and Technology of China, Kejiang Chen University of Science and Technology of China, Han Gao University of Science and Technology of China, Shaoyin Cheng University of Science and Technology of China, Weiming Zhang University of Science and Technology of China
Media Attached File Attached
14:30
12m
Talk
Generating Variable Explanations via Zero-shot Prompt LearningRecorded talk
Research Papers
Chong Wang Fudan University, Yiling Lou Fudan University, Liu Junwei Fudan University, Xin Peng Fudan University
Media Attached