EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Discrete Adversarial Attack to Models of Code

Fengjuan Gao, Yu Wang, Ke Wang

Proceedings of the ACM on Programming Languages · 06.06.2023 · 7 (PLDI) · 172-195

DOI: 10.1145/3591227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 06.06.2023. Verfasst von Fengjuan Gao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The pervasive brittleness of deep neural networks has attracted significant attention in recent years. A particularly interesting finding is the existence of adversarial examples, imperceptibly perturbed natural inputs that induce erroneous predictions in state-of-the-art neural models. In this paper, we study a different type of adversarial examples specific to code models, called discrete adversarial examples , which are created through program transformations that preserve the semantics of original inputs.In particular, we propose a novel, general method that is highly effective in attacking a broad range of code models. From the defense perspective, our primary contribution is a theoretical foundation for the application of adversarial training — the most successful algorithm for training robust classifiers — to defending code models against discrete adversarial attack. Motivated by the theoretical results, we present a simple realization of adversarial training that substantially improves the robustness of code models against adversarial attacks in practice. We extensively evaluate both our attack and defense methods. Results show that our discrete attack is significantly more effective than state-of-the-art whether or not defense mechanisms are in place to aid models in resisting attacks. In addition, our realization of adversarial training improves the robustness of all evaluated models by the widest margin against state-of-the-art adversarial attacks as well as our own.

Zitieren

APA

Gao, F., Wang, Y., & Wang, K. (2023). Discrete Adversarial Attack to Models of Code. Proceedings of the ACM on Programming Languages, 7(PLDI), 172-195. https://doi.org/10.1145/3591227

Vancouver

Gao F, Wang Y, Wang K. Discrete Adversarial Attack to Models of Code. Proceedings of the ACM on Programming Languages. 2023;7(PLDI):172-195. doi:10.1145/3591227

BibTeX
@article{Gao2023,
  author = {Gao, Fengjuan and Wang, Yu and Wang, Ke},
  title = {Discrete Adversarial Attack to Models of Code},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2023},
  volume = {7},
  number = {PLDI},
  pages = {172--195},
  doi = {10.1145/3591227}
}
Kostenlos starten →