Scholarlink

<p>Advanced neural text classifiers&#xa0;have shown remarkable ability in the task of classification. The investigation illustrates that text classification models have an inherent vulnerability to&#xa0;adversarial texts, where a few words or characters are altered to create adversarial examples that misleads the machine into making incorrect predictions while&#xa0;preserving its intended meaning among human viewers. The present study introduces Inflect-Text, a novel approach for attacking text that works at the level of individual words in a situation where the inner workings of the system are unknown. The objective is to deceive a specific neural text classifier while following specified language limitations in a manner that makes the changes undetectable to humans. Extensive investigations are carried out to evaluate the viability of the proposed attack methodology on various often utilized frameworks, inclusive of Word-CNN, Bi-LSTM and three advanced transformer models, across two benchmark datasets: AG news and MR, which are commonly employed for text classification tasks. Experimental results show that the suggested attack architecture regularly outperforms conventional methods by achieving much higher attack success rates and generating better adversarial examples. The findings suggest that neural text classifiers can be bypassed, which could have substantial ramifications for existing policy approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Inflect-text: a novel mechanism to evade neural text classifiers by leveraging word inflectional perturbations

  • 期刊论文

  • 发表日期：

    2025年1月26日

查看全文
  • Ashish Bajaj,
  • Dinesh Kumar Vishwakarma

摘要

Advanced neural text classifiers have shown remarkable ability in the task of classification. The investigation illustrates that text classification models have an inherent vulnerability to adversarial texts, where a few words or characters are altered to create adversarial examples that misleads the machine into making incorrect predictions while preserving its intended meaning among human viewers. The present study introduces Inflect-Text, a novel approach for attacking text that works at the level of individual words in a situation where the inner workings of the system are unknown. The objective is to deceive a specific neural text classifier while following specified language limitations in a manner that makes the changes undetectable to humans. Extensive investigations are carried out to evaluate the viability of the proposed attack methodology on various often utilized frameworks, inclusive of Word-CNN, Bi-LSTM and three advanced transformer models, across two benchmark datasets: AG news and MR, which are commonly employed for text classification tasks. Experimental results show that the suggested attack architecture regularly outperforms conventional methods by achieving much higher attack success rates and generating better adversarial examples. The findings suggest that neural text classifiers can be bypassed, which could have substantial ramifications for existing policy approaches.