Enhancing Function Name Prediction using Votes-Based Name Tokenization and Multi-task Learning

Reverse engineers would acquire valuable insights from descriptive function names, which are absent in publicly released binaries. Recent advances in binary function name prediction using data-driven machine learning show promise. However, existing approaches encounter difficulties in capturing function semantics in diverse optimized binaries and fail to reserve the meaning of labels in function names. We propose E pitome , a framework that enhances function name prediction using votes-based name tokenization and multi-task learning, specifically tailored for different compilation optimization binaries. E pitome learns comprehensive function semantics by pre-trained assembly language model and graph neural network, incorporating function semantics similarity prediction task, to maximize the similarity of function semantics in the context of different compilation optimization levels. In addition, we present two data preprocessing methods to improve the comprehensibility of function names. We evaluate the performance of E pitome using <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> mml:mrow mml:mn2</mml:mn> mml:mo,</mml:mo> mml:mn597</mml:mn> mml:mo,</mml:mo> mml:mn346</mml:mn> </mml:mrow> </mml:math> functions extracted from binaries compiled with 5 optimizations (O0-Os) for 4 architectures (x64, x86, ARM, and MIPS). E pitome outperforms the state-of-the-art function name prediction tool by up to <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> mml:mn44.34</mml:mn> mml:mo%</mml:mo> </mml:math> , <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> mml:mn64.16</mml:mn> mml:mo%</mml:mo> </mml:math> , and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> mml:mn54.44</mml:mn> mml:mo%</mml:mo> </mml:math> in precision, recall, and F1 score, while also exhibiting superior generalizability.