EUVIMEDEUVIMED entdecken
Crossref

Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process

Mingze Ni, Zhensu Sun, Wei Liu

IEEE Transactions on Knowledge and Data Engineering · 2024-07 · 36 (7) · 3062-3075

DOI: 10.1109/tkde.2024.3349708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2024-07. Verfasst von Mingze Ni und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 49 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent research has revealed that natural language processing (NLP) models are vulnerable to adversarial examples. However, the current techniques for generating such examples rely on deterministic heuristic rules, which fail to produce optimal adversarial examples. In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success. FBA uses the Metropolis-Hasting sampler, a type of Markov Chain Monte Carlo sampler, to improve the selection of adversarial examples from all candidates generated by a customized stochastic process called the Word Manipulation Process (WMP). The WMP method modifies individual words in a contextually-aware manner through insertion, removal, or substitution. Through extensive experiments, this study demonstrates that FBA outperforms other methods in terms of attack success rate, imperceptibility and sentence quality.

Zitieren

APA

Ni, M., Sun, Z., & Liu, W. (2024). Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process. IEEE Transactions on Knowledge and Data Engineering, 36(7), 3062-3075. https://doi.org/10.1109/tkde.2024.3349708

Vancouver

Ni M, Sun Z, Liu W. Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process. IEEE Transactions on Knowledge and Data Engineering. 2024;36(7):3062-3075. doi:10.1109/tkde.2024.3349708

BibTeX
@article{Ni2024,
  author = {Ni, Mingze and Sun, Zhensu and Liu, Wei},
  title = {Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2024},
  volume = {36},
  number = {7},
  pages = {3062--3075},
  doi = {10.1109/tkde.2024.3349708}
}
Kostenlos starten →