Fast, Fine-Grained Equivalence Checking for Neural Decompilers

Le résumé fourni par la source

Neural decompilers are machine learning models that reconstruct the source code from an executable program. Critical to the lifecycle of any machine learning model is an evaluation of its effectiveness. However, existing techniques for evaluating neural decompilation models are generally inadequate, especially when it comes to showing the correctness of the neural decompiler’s predictions. To address this, we introduce codealign , a novel instruction-level code equivalence technique designed for neural decompilers. We provide a formal definition of a relation between equivalent instructions, which we term an equivalence alignment. We show how codealign generates equivalence alignments and then evaluate codealign by comparing it with symbolic execution. Finally, we show how the information codealign provides—which parts of the functions are equivalent and how well the variable names match—is substantially more detailed than existing state-of-the-art evaluation metrics, which report unitless numbers measuring similarity.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.