Tomás Pelayo-Benedet (Universidad de Zaragoza), Kevin Borgolte (Ruhr University Bochum), Ricardo J. Rodríguez (Universidad de Zaragoza)

Binary decompilation remains an open challenge in reverse engineering. While recent approaches have begun to leverage the capabilities of large language models (LLMs), most continue to focus exclusively on disassembly as input, ignoring the intermediate representations (IRs) employed by static binary analysis tools and traditional decompilers.

In this paper, we present the first systematic evaluation of LLM-based decompilation using hierarchical IRs. In particular, we investigate how different levels of abstraction in IRs affect binary decompilation quality in five commercial LLMs. Our findings show that the choice of IR significantly influences performance: Smaller models benefit markedly from high-level structured IRs, while larger models show stable performance across IR levels. Our evaluation also reveals a significant trade-off between recompilation success and functional correctness. Code decompiled from disassembly tends to recompile more reliably, but it is less often functionally correct. In contrast, code decompiled from high-level IRs more often retains the original functionality, albeit with slightly lower recompilation success rates. Furthermore, we find that cognitive complexity metrics, such as Halstead measures, are strong predictors of decompilation difficulty, while traditional structural metrics, such as cyclomatic complexity, offer limited insight. We also highlight the main lines of research to improve binary decompilation by combining the advantages of static binary analysis techniques with the capabilities of modern LLMs.

View More Papers

Work-in-progress: Uncovering the Invisible: A Large-Scale Analysis of Service...

Sivakanesan Dhanushkanda (Old Dominion University), Mustafa Ibrahim (Old Dominion University), Shuai Hao (Old Dominion University)

Read More

Small Cell, Big Risk: A Security Assessment of 4G...

Yaru Yang (Tsinghua University), Yiming Zhang (Tsinghua University), Tao Wan (CableLabs & Carleton University), Haixin Duan (Tsinghua University & Quancheng Laboratory), Deliang Chang (QI-ANXIN Technology Research Institute), Yishen Li (Tsinghua University), Shujun Tang (Tsinghua University & QI-ANXIN Technology Research Institute)

Read More

What Are Brands Telling You About Smishing? A Cross-Industry...

Dev Vikesh Doshi (California State University San Marcos), Mehjabeen Tasnim (California State University San Marcos), Fernando Landeros (California State University San Marcos), Chinthagumpala Muni Venkatesh (California State University San Marcos), Daniel Timko (Emerging Threats Lab / Smishtank.com), Muhammad Lutfor Rahman (California State University San Marcos)

Read More