Unleashing the Power of Generative Model in Recovering Variable Names from Stripped Binary

—Decompilation aims to recover the source code form of a binary executable. It has many security applications, such as malware analysis, vulnerability detection, and code hardening. A prominent challenge in decompilation is to recover variable names. We propose a novel technique that leverages the strengths of generative models while mitigating model biases. We build a prototype, G EN N M , from pre-trained generative models CodeGemma-2B, CodeLlama-7B, and CodeLlama-34B. We fine-tune G EN N M on decompiled functions and teach models to leverage contextual information. G EN N M includes names from callers and callees while querying a function, providing rich contextual information within the model’s input token limitation. We mitigate model biases by aligning the output distribution of models with symbol preferences of developers. Our results show that G EN N M improves the state-of-the-art name recovery precision by 5.6–11.4 percentage points on two commonly used datasets and improves the state-of-the-art by 32% (from 17.3% to 22.8%) in the most challenging setup where ground-truth variable names are not seen in the training dataset.