Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

2022/10/20 by Hannah Chen, Chen, Hannah, Yangfeng Ji +3
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2210.11498

openalex publication_date 2022/10/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur when an adversary finds a small perturbation that preserves the classifier's prediction but changes the true label of an input. Adversarial training and certified robust training have shown some effectiveness in improving the robustness of machine learnt models to fickle adversarial examples. We show that standard adversarial training methods focused on reducing vulnerability to fickle adversarial examples may make a model more vulnerable to obstinate adversarial examples, with experiments for both natural language inference and paraphrase identification tasks. To counter this phenomenon, we introduce Balanced Adversarial Training, which incorporates contrastive learning to increase robustness against both fickle and obstinate adversarial examples.

Related

• Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
• How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
• Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion
• Splitting the Difference on Adversarial Training
• Recent Advances in Adversarial Training for Adversarial Robustness