AID: Lightweight Disassembly via Learning-Superset-Learning-Recursive Algorithm
Open Access
- 13 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Abstract
Disassembly remains the foundation of binary analysis tasks but continues to face many significant challenges that hurt precision, recall, or speed. In this paper, we propose a lightweight disassembly approach called AID that strikes an effective balance between precision, recall, and speed. At the core, it first fuses superset disassembly and a learning-based approach to identify potential code entries with high recall and precision. Then it uses recursive disassembly to recover instructions with high precision. We implemented a prototype of AID and evaluated it across various datasets, including real-world binaries, large-size binaries, and complex binaries. Experiments demonstrate that AID delivers exceptional performance in terms of speed, precision, and recall. Its speed is comparable to that of IDA Pro and DeepDi, but significantly faster than Angr, Ddisasm, Ghidra, and DASSA. On the SPEC2017 dataset, AID reduces missed instructions (i.e., false negatives) by 1.68 to 148 times compared to baselines and reduces erroneous instructions (i.e., false positives) by 1.49 to 1,243 times.Keywords
This publication has 24 references indexed in Scilit:
- Disassembly as Weighted Interval Scheduling with Learned Weights2025
- The Good, the Bad, and the Binary: An LSTM-Based Method for Section Boundary Detection in Firmware Analysis2023
- D-ARM: Disassembling ARM Binaries by Lightweight Superset Instruction Interpretation and Graph Modeling2023
- Code Action Network for Binary Function Scope IdentificationLecture Notes in Computer Science, 2020
- Probabilistic Disassembly2019
- Function Interface Analysis: A Principled Approach for Function Recognition in COTS Binaries2017
- SOK: (State of) The Art of War: Offensive Techniques in Binary Analysis2016
- Repeatable Reverse Engineering with PANDA2015
- Obfuscator-LLVM -- Software Protection for the Masses2015
- Practical analysis of stripped binary codeACM SIGARCH Computer Architecture News, 2005