Xiangzhe Xu
Computer Science · Purdue University West Lafayette
Publications
42
Citations
286
Est. group size
~8
Recurring co-author estimate
Active years
7
Publishing since 2020
Xiangzhe Xu works on software security and program analysis, with a strong recent focus on combining large language models (LLMs) with tools for analyzing binary code (compiled programs without source code) and detecting bugs, malware, and vulnerabilities. Work includes building LLM-based agents that recover meaningful information (like variable names and data structures) from stripped binaries, analyze data flow in code, and audit repositories for security bugs, as well as studying how safe AI coding assistants are against misuse. This research sits at the intersection of software engineering, security verification, and machine learning applied to code.
Publication output was minimal before 2020, rose sharply from 2023 to 2024, and has continued at a notable pace into 2025-2026, indicating a growing and increasingly active research output in recent years.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
Open MIND · 2026
- Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
arXiv (Cornell University) · 2026
- When Harmful Intent Dissolves into Technical Detail: How Safe Are Coding Agents Against Cyber Misuse?
2026
- RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
arXiv (Cornell University) · 2025
- Transformer and Its Application and Advances in Text Generation
Advances in engineering research/Advances in Engineering Research · 2025
- Position: Intelligent Coding Systems Should Write Programs with Justifications
arXiv (Cornell University) · 2025
- <scp>ARCTURUS</scp> : Full Coverage Binary Similarity Analysis with Reachability-guided Emulation
ACM Transactions on Software Engineering and Methodology · 2024
- Enhanced removal characteristics of Raphidiopsis raciborskii and dissolved organic matter by a novel preozonation-coagulation/ozonation process using micro-nano bubbles
Separation and Purification Technology · 2024
- CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
Proceedings of the ACM on software engineering. · 2024
- ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries
2024
- Sanitizing Large Language Models in Bug Detection with Data-Flow
2024
- LLMDFA: Analyzing Dataflow in Code with Large Language Models
arXiv (Cornell University) · 2024
- LLMDFA: Analyzing Dataflow in Code with Large Language Models
2024
- CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking
arXiv (Cornell University) · 2024
- Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
arXiv (Cornell University) · 2024
- arXiv (Cornell University)×16
- Proceedings of the ACM on Programming Languages×2
- Lecture notes in computer science×2
- ACM Transactions on Software Engineering and Methodology×1
- Algal Research×1
- Huaijin Wang
Computer Science · The Ohio State University
- Aravind Machiry
Computer Science · Purdue University West Lafayette
- Zhuo Zhang
Computer Science · Purdue University West Lafayette
- Carter Yagemann
Computer Science · The Ohio State University
- Chaoshun Zuo
Computer Science · The Ohio State University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile