A Modified Word Saliency-Based Adversarial Attack on Text Classification Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908358073647104 |
|---|---|
| author | Waghela, Hetvi Rakshit, Sneha Sen, Jaydip |
| author_facet | Waghela, Hetvi Rakshit, Sneha Sen, Jaydip |
| contents | This paper introduces a novel adversarial attack method targeting text classification models, termed the Modified Word Saliency-based Adversarial At-tack (MWSAA). The technique builds upon the concept of word saliency to strategically perturb input texts, aiming to mislead classification models while preserving semantic coherence. By refining the traditional adversarial attack approach, MWSAA significantly enhances its efficacy in evading detection by classification systems. The methodology involves first identifying salient words in the input text through a saliency estimation process, which prioritizes words most influential to the model's decision-making process. Subsequently, these salient words are subjected to carefully crafted modifications, guided by semantic similarity metrics to ensure that the altered text remains coherent and retains its original meaning. Empirical evaluations conducted on diverse text classification datasets demonstrate the effectiveness of the proposed method in generating adversarial examples capable of successfully deceiving state-of-the-art classification models. Comparative analyses with existing adversarial attack techniques further indicate the superiority of the proposed approach in terms of both attack success rate and preservation of text coherence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11297 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Modified Word Saliency-Based Adversarial Attack on Text Classification Models Waghela, Hetvi Rakshit, Sneha Sen, Jaydip Computation and Language Cryptography and Security Machine Learning This paper introduces a novel adversarial attack method targeting text classification models, termed the Modified Word Saliency-based Adversarial At-tack (MWSAA). The technique builds upon the concept of word saliency to strategically perturb input texts, aiming to mislead classification models while preserving semantic coherence. By refining the traditional adversarial attack approach, MWSAA significantly enhances its efficacy in evading detection by classification systems. The methodology involves first identifying salient words in the input text through a saliency estimation process, which prioritizes words most influential to the model's decision-making process. Subsequently, these salient words are subjected to carefully crafted modifications, guided by semantic similarity metrics to ensure that the altered text remains coherent and retains its original meaning. Empirical evaluations conducted on diverse text classification datasets demonstrate the effectiveness of the proposed method in generating adversarial examples capable of successfully deceiving state-of-the-art classification models. Comparative analyses with existing adversarial attack techniques further indicate the superiority of the proposed approach in terms of both attack success rate and preservation of text coherence. |
| title | A Modified Word Saliency-Based Adversarial Attack on Text Classification Models |
| topic | Computation and Language Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2403.11297 |