GenFighter: A Generative and Evolutive Textual Attack Removal
This addresses the problem of adversarial robustness for NLP systems, offering an incremental improvement over existing defenses.
The paper tackles adversarial attacks on Transformer models in NLP by introducing GenFighter, a defense strategy that identifies and transforms malicious instances to improve robustness, resulting in outperforming state-of-the-art defenses in accuracy under attack and attack success rate metrics.
Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution. GenFighter identifies potentially malicious instances deviating from the distribution, transforms them into semantically equivalent instances aligned with the training data, and employs ensemble techniques for a unified and robust response. By conducting extensive experiments, we show that GenFighter outperforms state-of-the-art defenses in accuracy under attack and attack success rate metrics. Additionally, it requires a high number of queries per attack, making the attack more challenging in real scenarios. The ablation study shows that our approach integrates transfer learning, a generative/evolutive procedure, and an ensemble method, providing an effective defense against NLP adversarial attacks.