Code Vectors: Understanding Programs Through Embedded Abstracted Symbolic Traces

TL;DR

This paper introduces a novel approach to program understanding by transforming symbolic execution traces into embeddings, achieving high accuracy on API-usage analogy tasks and demonstrating the effectiveness of semantic abstractions.

Contribution

The paper presents a new method for representing programs using embeddings of symbolic execution traces, highlighting the importance of semantic abstractions for improved accuracy.

Findings

Achieved 93% top-1 accuracy on API-usage analogy benchmark.

Semantic abstractions significantly outperform syntactic ones in embedding quality.

Embeddings trained with various parameters show robustness across tasks.

Abstract

With the rise of machine learning, there is a great deal of interest in treating programs as data to be fed to learning algorithms. However, programs do not start off in a form that is immediately amenable to most off-the-shelf learning techniques. Instead, it is necessary to transform the program to a suitable representation before a learning technique can be applied. In this paper, we use abstractions of traces obtained from symbolic execution of a program as a representation for learning word embeddings. We trained a variety of word embeddings under hundreds of parameterizations, and evaluated each learned embedding on a suite of different tasks. In our evaluation, we obtain 93% top-1 accuracy on a benchmark consisting of over 19,000 API-usage analogies extracted from the Linux kernel. In addition, we show that embeddings learned from (mainly) semantic abstractions provide nearly triple the accuracy of those learned from (mainly) syntactic abstractions.