|国家预印本平台
首页|Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach

Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach

Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach

来源:Arxiv_logoArxiv
英文摘要

Despite advancements in Natural Language Processing (NLP), models remain vulnerable to adversarial attacks, such as synonym substitutions. While prior work has focused on improving robustness for feed-forward and convolutional architectures, the robustness of recurrent networks and modern state space models (SSMs), such as S4, remains understudied. These architectures pose unique challenges due to their sequential processing and complex parameter dynamics. In this paper, we introduce a novel regularization technique based on Growth Bound Matrices (GBM) to improve NLP model robustness by reducing the impact of input perturbations on model outputs. We focus on computing the GBM for three architectures: Long Short-Term Memory (LSTM), State Space models (S4), and Convolutional Neural Networks (CNN). Our method aims to (1) enhance resilience against word substitution attacks, (2) improve generalization on clean text, and (3) providing the first systematic analysis of SSM (S4) robustness. Extensive experiments across multiple architectures and benchmark datasets demonstrate that our method improves adversarial robustness by up to 8.8% over existing baselines. These results highlight the effectiveness of our approach, outperforming several state-of-the-art methods in adversarial defense. Codes are available at https://github.com/BouriMohammed/GBM

Mohammed Bouri、Adnane Saoud

计算技术、计算机技术

Mohammed Bouri,Adnane Saoud.Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach[EB/OL].(2025-07-14)[2025-08-02].https://arxiv.org/abs/2507.10330.点此复制

评论