Software Reverse Engineering

Follow this topic Ask about this topic

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

35 papers4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Neural architectures for resolving references in program code
Apr 15, 2026Gergő Szalay, Gergely Zsolt Kovács, Sándor Teleki +2Sequence-to-Sequence Models Neural Algorithmic Reasoning
Faculty of Informatics, ELTE Eötvös Loránd University, Budapest, H-1117
CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
Apr 14, 2026Qiang Zhang, Zhongnian LiAdaptive Inference Software Reverse Engineering
School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China · Mine Digitization Engineering Research Center of the Ministry of Education, China University of Mining and Technology, Xuzhou, China
LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering
Apr 7, 2026Hamed Jelodar, Samita Bai, Tochukwu Emmanuel Nwankwo +4Software Reverse Engineering Malware Analysis
Faculty of Computer Science, University of New Brunswick, Canada
CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
Apr 4, 2026Baicheng Chen, Yu Wang, Ziheng Zhou +4Software Reverse Engineering LLMs for Cybersecurity
Shanghai Qi Zhi Institute · The Chinese University of Hong Kong, Shenzhen · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +4
PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent
Mar 16, 2026Yuxin Cui, Zeyu Gao, Shuxian He +2Code Translation Software Reverse Engineering
Tsinghua University · Wuhan University · Institute of Information Engineering, CAS

Apr 15, 2026J/K move · Enter open · S save

Neural architectures for resolving references in program code

Gergő Szalay, Gergely Zsolt Kovács, Sándor Teleki, Balázs Pintér+1

Faculty of Informatics, ELTE Eötvös Loránd University, Budapest, H-1117

Sequence-to-Sequence Models Neural Algorithmic Reasoning Sequence Modeling Software Reverse Engineering

Open paper AskPDF arXiv

Resolving and rewriting references is fundamental in programming languages. Motivated by a real-world decompilation task, we abstract reference rewriting into the problems of direct and indirect indexing by permutation. We create synthetic benchmarks for these tasks and show that well-known sequence-to-sequence machine learning architectures are struggling on these benchmarks. We introduce new sequence-to-sequence architectures for both problems. Our measurements show that our architectures outperform the baselines in both robustness and scalability: our models can handle examples that are ten times longer compared to the best baseline. We measure the impact of our architecture in the real-world task of decompiling switch statements, which has an indexing subtask. According to our measurements, the extended model decreases the error rate by 42%. Multiple ablation studies show that all components of our architectures are essential.

Latest papers

Neural architectures for resolving references in program code

CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent