Software Reverse Engineering

Overview

Software reverse engineering infers a program’s logic, interfaces, and security properties from compiled code, especially stripped or obfuscated binaries, supporting maintenance, malware analysis, and vulnerability discovery. Methods combine disassembly and static analysis with dynamic execution, emulation, fuzzing, and source-to-binary matching; neural decompilers and large language model agents increasingly assist with pseudocode recovery and analyst workflows. Evaluation spans function-matching and decompilation benchmarks, challenge binaries, and executable tests, since readability, compilation, and similarity scores do not guarantee behavioral equivalence. Work increasingly uses tool-using agents and execution-guided repair, but obfuscation, scale, trustworthy ground truth, prompt-injection risks, and the gap between model and expert performance remain central challenges.

Latest papers

CardsList

38 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. More Context, Mixed Results: Evaluating LLMs for Identifier Recovery and Code Deobfuscation

    Nov 14, 2026Simon Queyrut, Valerio Schiavoni, Giuseppe Antonio Di Luna +3Software Reverse EngineeringCode Language Models

  2. CyberBinGym: Can AI Agents Turn Binary Patches into Real Exploits?

    Nov 7, 2026Lambang Akbar Wijayadi, Zhaoqi Xiao, Zhun Wang +5Automated Exploit GenerationAI Agent Security Benchmarks

  3. Rethinking Neural Decompilation: Candidate Selection as the Hidden Bottleneck

    Nov 2, 2026Felix Mächtle, Gautham Sriram, Manjil Neupane +2Software Reverse EngineeringMalware Analysis

  4. VulDec: Vulnerability Detection in Binaries via Neural Decompilation

    Oct 24, 2026Francesco Crescenzo Grasso, Pietro Liguori, Roberto Natella +1Software Vulnerability DetectionSoftware Reverse Engineering

  5. ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation

    Oct 20, 2026Akarsh Ashok, Dinil Mon Divakaran, Vivek BalachandranBenchmark DesignSoftware Engineering Benchmarks

  6. Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering

    Oct 10, 2026Samuele Doria, Stefano De Rosa, Ruoyu Wang +3Software Reverse EngineeringLLM Agent Evaluation

  7. Echo: Learning-based Matching Decompilation using Trusted Back Translation

    Sep 16, 2026Jun Bi, Xiangxin Fang, Aarsh Chaube +3Software Reverse EngineeringProgram Synthesis

  8. Recompilation Is Not Enough: Test-Guided Decompiled-C Repair

    Sep 7, 2026Yuhan Huang, Puzhuo Liu, Jianlei ChiAutomated Program RepairSoftware Reverse Engineering

  9. When LLM Decompilers Recompile More and Preserve Less

    Sep 4, 2026Chang Liu, Edward Raff, Kristopher MicinskiSoftware Reverse EngineeringDifferential Testing

  10. Instruction Alignment for Binary Code Representation Learning

    Aug 12, 2026Huaijin Wang, Shuai WangSoftware EngineeringRepresentation Learning

  11. The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark

    Aug 11, 2026Jeremy Spence, Nicholas Assaderaghi, Feng Xiao +9Software Reverse EngineeringAI Agent Security Benchmarks

  12. Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering

    Aug 7, 2026Xiuwei Shang, Li Hu, Xiao Jiang +7LLM-as-a-JudgeSoftware Reverse Engineering

  13. Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

    Jul 10, 2026Charles Edward Gagnon, Steven H. H. Ding, Philippe Charland +1Software EngineeringSoftware Reverse Engineering

  14. REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

    Jul 7, 2026Nicolas Koller, Andreas U. SchmidtLLM EvaluationSoftware Reverse Engineering

  15. Evaluating Neural Decompilation of Dart AOT Binaries: Fine-Tuning, Metric Validity, Specification Leakage, and Reliability

    Jul 7, 2026Raafat Abualazm, Ayman AboElhassan, Amr G. WassalSoftware EngineeringLLM Evaluation

  16. Multi-View Decompilation for LLM-Based Malware Classification

    Jun 18, 2026Bercan Turkmen, Vyas RainaSoftware Reverse EngineeringLLM Prompting

  17. SoK: AI-Augmented Binary Reversing

    Jun 16, 2026Yujeong Kwon, Yiyue Zhang, Shakhzod Yuldoshkhujaev +3Software Reverse Engineering

  18. Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents

    May 29, 2026Brian Crawford, Patrick McClureSoftware Reverse EngineeringIndirect Prompt Injection

  19. Automatically Attacking Software Reverse Engineering AI Agents

    May 28, 2026Brian Crawford, Justin Phillips, Patrick McClureSoftware EngineeringAdversarial Prompt Generation

  20. Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents

    May 18, 2026Sanderson Oliveira de Macedo, Ronaldo Martins da CostaSoftware EngineeringSoftware Engineering Agents

  21. Decaf: Improving Neural Decompilation with Automatic Feedback and Search

    May 12, 2026Alexander Shypula, Osbert Bastani, Edward SchwartzSoftware Reverse EngineeringCompiler-Guided Program Synthesis

  22. CrackMeBench: Binary Reverse Engineering for Agents

    May 11, 2026Isaac David, Arthur GervaisSoftware Reverse EngineeringLLM Agent Evaluation

  23. Agentic Vulnerability Reasoning on COTS Binaries

    May 6, 2026Hwiwon Lee, Jongseong Kim, Lingming ZhangSoftware Reverse EngineeringSoftware Vulnerability Detection

  24. Identifier-Free Code Embedding Models for Scalable Search

    May 5, 2026Eric Wolos, Michael DoyleSoftware Reverse Engineering

  25. REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)

    Apr 30, 2026Jun Yeon Won, Xin Jin, Shiqing Ma +1LLM EvaluationSoftware Reverse Engineering