EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial natural language processing: overview, challenges, and policy implications

Laxmi Shaw, Mohammed Wasim Ansari, Tahir Ekin

Data & Policy · 2025 · 7

DOI: 10.1017/dap.2025.10030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data & Policy, online erschienen am 22.09.2025. Verfasst von Laxmi Shaw und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Division of Information and Intelligent Systems, Air Force Office of Scientific Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The emergence of large language models has significantly expanded the use of natural language processing (NLP), even as it has heightened exposure to adversarial threats. We present an overview of adversarial NLP with an emphasis on challenges, policy implications, emerging areas, and future directions. First, we review attack methods and evaluate the vulnerabilities of popular NLP models. Then, we review defense strategies that include adversarial training. We describe major policy implications, identify key trends, and suggest future directions, such as the use of Bayesian methods to improve the security and robustness of NLP systems.

Förderung

  • Division of Information and Intelligent Systems
  • Air Force Office of Scientific Research

Zitieren

APA

Shaw, L., Ansari, M. W., & Ekin, T. (2025). Adversarial natural language processing: overview, challenges, and policy implications. Data & Policy, 7. https://doi.org/10.1017/dap.2025.10030

Vancouver

Shaw L, Ansari MW, Ekin T. Adversarial natural language processing: overview, challenges, and policy implications. Data & Policy. 2025;7. doi:10.1017/dap.2025.10030

BibTeX
@article{Shaw2025,
  author = {Shaw, Laxmi and Ansari, Mohammed Wasim and Ekin, Tahir},
  title = {Adversarial natural language processing: overview, challenges, and policy implications},
  journal = {Data & Policy},
  year = {2025},
  volume = {7},
  doi = {10.1017/dap.2025.10030}
}
Kostenlos starten →