Scholarlink

<p>Traditional decompilers utilize countless hardcoded rules written by subject matter experts, making them inflexible. Some recent systems address this using deep learning. The current consensus is that these systems have to include considerable domain knowledge and iterative heuristic components to solve parts of the decompilation problem, particularly the problem of predicting identifiers and literals. In this paper, we present a <i>single-pass</i> <i>end-to-end</i> neural decompilation system that utilizes <i>copying mechanism</i>. The copying mechanism is able to copy the literals and (offsets of) variables directly from the assembly code, in a <i>single step</i>, as part of the <i>single forward pass</i> through the model. Additionally, we take a further step toward decompiling real-world code by addressing important programming constructs like switch statements, function definitions, and function calls. We compile a dataset of real-world programming competition code and evaluate our model on it. The method achieves a program accuracy of 73% on the hardest complexity level of our generated dataset and 51% on the real-world examples without any additional error correction (EC) techniques, which surpasses the results of previous works without EC.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Single-pass end-to-end neural decompilation using copying mechanism

  • 期刊论文

  • 发表日期：

    2024年12月31日

查看全文
  • Gergő Szalay,
  • Máté Bálint Poór,
  • Balázs Pintér,
  • Tibor Gregorics

摘要

Traditional decompilers utilize countless hardcoded rules written by subject matter experts, making them inflexible. Some recent systems address this using deep learning. The current consensus is that these systems have to include considerable domain knowledge and iterative heuristic components to solve parts of the decompilation problem, particularly the problem of predicting identifiers and literals. In this paper, we present a single-pass end-to-end neural decompilation system that utilizes copying mechanism. The copying mechanism is able to copy the literals and (offsets of) variables directly from the assembly code, in a single step, as part of the single forward pass through the model. Additionally, we take a further step toward decompiling real-world code by addressing important programming constructs like switch statements, function definitions, and function calls. We compile a dataset of real-world programming competition code and evaluate our model on it. The method achieves a program accuracy of 73% on the hardest complexity level of our generated dataset and 51% on the real-world examples without any additional error correction (EC) techniques, which surpasses the results of previous works without EC.