Natural Attack for Pre-trained Models of Code

Zhou Yang, Jieke Shi, Junda He, David Lo

Abstract

Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.

BibTeX

@inproceedings{Yang-al:ICSE22,
  author    = {Zhou Yang and
               Jieke Shi and
               Junda He and
               David Lo},
  title     = {Natural Attack for Pre-trained Models of Code},
  booktitle = {ICSE},
  pages     = {1482--1493},
  publisher = {{ACM}},
  year      = {2022},
}

Natural Attack for Pre-trained Models of Code

Abstract

Related papers