Tady: A Neural Disassembler without Structural Constraint Violations

TL;DR

Tady is a neural disassembler that enforces structural constraints to improve accuracy and reliability in binary analysis, addressing limitations of previous models by integrating formal constraints and post-processing.

Contribution

The paper introduces Tady, a neural disassembler that incorporates structural constraints based on post-dominance relations to eliminate violations and improve disassembly quality.

Findings

Tady effectively removes structural violations in disassembly outputs.

Tady maintains high instruction-level accuracy while ensuring structural integrity.

The approach demonstrates high efficiency across diverse binaries.

Abstract

Disassembly is a crucial yet challenging step in binary analysis. While emerging neural disassemblers show promise for efficiency and accuracy, they frequently generate outputs violating fundamental structural constraints, which significantly compromise their practical usability. To address this critical problem, we regularize the disassembly solution space by formalizing and applying key structural constraints based on post-dominance relations. This approach systematically detects widespread errors in existing neural disassemblers' outputs. These errors often originate from models' limited context modeling and instruction-level decoding that neglect global structural integrity. We introduce Tady, a novel neural disassembler featuring an improved model architecture and a dedicated post-processing algorithm, specifically engineered to address these deficiencies. Comprehensive evaluations on diverse binaries demonstrate that Tady effectively eliminates structural constraint violations and functions with high efficiency, while maintaining instruction-level accuracy.