Abstract
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.
Abstract (translated)
对抗性攻击对深度神经网络（DNNs）如Transformer模型在自然语言处理（NLP）中构成了重大挑战。本文提出了一种名为GenFighter的新防御策略，通过在训练分类分布上学习和推理来增强对抗性鲁棒性。GenFighter能够识别出分布中可能存在恶意实例，并将它们转化为与训练数据平行的语义等价实例，并采用集成技术实现统一和鲁棒的攻击响应。通过进行大量实验，我们发现GenFighter在攻击和攻击成功率指标上优于最先进的防御措施。此外，它需要每个攻击很高的查询次数，使得在现实场景中攻击更加具有挑战性。消融研究证明了我们的方法集成了迁移学习、生成/进化过程和集成方法，有效对抗了NLP对抗攻击。
URL
https://arxiv.org/abs/2404.11538
