Grey-box Adversarial Attack And Defence For Sentiment Classification

2021/03/22 by Ying Xu, Xu, Ying, Xu Zhong +5 · 1 citation
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2103.11576

openalex publication_date 2021/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.

Citations

• Categorical Reparameterization with Gumbel-Softmax
• Adversarial Texts with Gradient Methods
• Certified Robustness to Adversarial Word Substitutions
• Elephant in the Room: An Evaluation Framework for Assessing Adversarial Examples in NLP

Cited by

• Text Adversarial Attacks with Dynamic Outputs

Related

• Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
• Adversarial Evasion Attack Efficiency against Large Language Models
• Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
• Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks
• TextDecepter: Hard Label Black Box Attack on Text Classifiers