Article: Adversarial machine learning algorithms for English translation quality estimation Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.61 pp.80 - 96 Abstract: Reliable evaluation of the quality of machine translation is essential to ensure a reliable automatic translation system. However, adversarial attacks can reduce evaluation performance by subtly disturbing sentences and endanger the security of key applications. This paper proposes a comprehensive confrontational robustness enhancement framework specially designed for translation quality evaluation, an adversarial robustness enhancement framework. The framework integrates a multi-grained confrontation sample generator, a dynamic confrontation training mechanism based on the relaxation of master and apprentice labels, and online defence module. The experiment was verified on the machine translation and multilingual quality evaluation seminar and post-editing task data set: this method increased the robustness of the model by 34.2%, reduced the average prediction error from 18.7% to 12.3% in the attack state. The framework shows stable performance in multiple fields providing an effective solution for building safe and reliable actual scene translation quality evaluation system. Inderscience Publishers - linking academia, business and industry through research

Title: Adversarial machine learning algorithms for English translation quality estimation

Authors: Sumei Dou

Addresses: Basic Teaching Department, Shangqiu Institute of Technology, Shangqiu, 476000, China

Abstract: Reliable evaluation of the quality of machine translation is essential to ensure a reliable automatic translation system. However, adversarial attacks can reduce evaluation performance by subtly disturbing sentences and endanger the security of key applications. This paper proposes a comprehensive confrontational robustness enhancement framework specially designed for translation quality evaluation, an adversarial robustness enhancement framework. The framework integrates a multi-grained confrontation sample generator, a dynamic confrontation training mechanism based on the relaxation of master and apprentice labels, and online defence module. The experiment was verified on the machine translation and multilingual quality evaluation seminar and post-editing task data set: this method increased the robustness of the model by 34.2%, reduced the average prediction error from 18.7% to 12.3% in the attack state. The framework shows stable performance in multiple fields providing an effective solution for building safe and reliable actual scene translation quality evaluation system.

Keywords: translation quality assessment; adversarial machine learning; robustness assessment; natural language processing; NLP; model security.

DOI: 10.1504/IJICT.2026.153940

International Journal of Information and Communication Technology, 2026 Vol.27 No.61, pp.80 - 96

Received: 02 Feb 2026
Accepted: 15 Mar 2026
Published online: 08 Jun 2026 *

Title: Adversarial machine learning algorithms for English translation quality estimation

Keep up-to-date