AID: Lightweight Disassembly via Learning-Superset-Learning-Recursive Algorithm

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.