SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Pandey, Saurabh Kumar Vashistha, Sachin Das, Debrup Aditya, Somak Choudhury, Monojit
Pandey, Saurabh Kumar
Vashistha, Sachin
Das, Debrup
Aditya, Somak
Choudhury, Monojit
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
To understand the complexity of sequence classification tasks, Hahn et al. (2021) proposed sensitivity as the number of disjoint subsets of the input sequence that can each be individually changed to change the output. Though effective, calculating sensitivity at scale using this framework is costly because of exponential time complexity. Therefore, we introduce a Sensitivity-based Multi Armed Bandit framework (SMAB), which provides a scalable approach for calculating word-level local (sentence-level) and global (aggregated) sensitivities concerning an underlying text classifier for any dataset. We establish the effectiveness of our approach through various applications. We perform a case study on CHECKLIST generated sentiment analysis dataset where we show that our algorithm indeed captures intuitively high and low-sensitive words. Through experiments on multiple tasks and languages, we show that sensitivity can serve as a proxy for accuracy in the absence of gold data. Lastly, we show that guiding perturbation prompts using sensitivity values in adversarial example generation improves attack success rate by 15.58%, whereas using sensitivity as an additional reward in adversarial paraphrase generation gives a 12.00% improvement over SOTA approaches.
Citation
S. K. Pandey, S. Vashistha, D. Das, S. Aditya, and M. Choudhury, “SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation,” pp. 9158–9176, Jun. 2025, doi: 10.18653/V1/2025.NAACL-LONG.463
Source
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Conference
2025 Conference of the North American Chapter of the Association for Computational Linguistics-NAACL
Keywords
Word Sensitivity Estimation, Multi-Armed Bandit, Adversarial Text Generation, Sensitivity Proxy, Adversarial Example Generation, NLP Robustness, Text Classification Sensitivity, Perturbation-Guided Prompts
Subjects
Source
2025 Conference of the North American Chapter of the Association for Computational Linguistics-NAACL
Publisher
Association for Computational Linguistics