International Journal of Informatics, Information System and Computer Engineering (INJIISCOM)
Vol. 6 No. 2 (2025): INJIISCOM: VOLUME 6, ISSUE 2, DECEMBER 2025

TextGuard: Identifying and Neutralizing Adversarial Threats in Textual Data

Luay Albtsoh (Dept. of Computer Science, Capitol Technology University, Maryland, USA)
Marwan Omar (Dept. of Computer Science, Capitol Technology University, Maryland, USA)



Article Info

Publish Date
14 Jan 2025

Abstract

Adversarial attacks in the text domain pose a serious risk to the integrity of Natural Language Processing (NLP) systems. In this study, we propose "TextGuard," a unique approach to detect hostile instances in NLP, based on the Local Outlier Factor (LOF) algorithm. This paper compares TextGuard's performance against traditional NLP classifiers like LSTM, CNN, and transformer-based models, experimentally verifying its effectiveness across various real-world datasets. To contextualize our findings and demonstrate its superiority, TextGuard significantly surpasses earlier state-of-the-art methods like DISP and FGWS, achieving F1 recognition accuracy scores up to 94.8%. Consequently, this sets a new benchmark as the first application of the LOF technique for adversarial example identification within the text domain.

Copyrights © 2025






Journal Info

Abbrev

injiiscom

Publisher

Subject

Computer Science & IT Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Description

FOCUS AND SCOPE INJIISCOM cover all topics under the fields of Computer Engineering, Information system, and Informatics. Informatics and Information system IT Audit Software Engineering Big Data and Data Mining Internet Of Thing (IoT) Game Development IT Management Computer Network and Security ...