A Survey of Adversarial Defenses and Robustness in NLP

Citations Over TimeTop 1% of 2023 papers

Abstract

In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong adversarial attacks for computer vision and Natural Language Processing (NLP) tasks. As a response, many defense mechanisms have also been proposed to prevent these networks from failing. The significance of defending neural networks against adversarial attacks lies in ensuring that the model’s predictions remain unchanged even if the input data is perturbed. Several methods for adversarial defense in NLP have been proposed, catering to different NLP tasks such as text classification, named entity recognition, and natural language inference. Some of these methods not only defend neural networks against adversarial attacks but also act as a regularization mechanism during training, saving the model from overfitting. This survey aims to review the various methods proposed for adversarial defenses in NLP over the past few years by introducing a novel taxonomy. The survey also highlights the fragility of advanced deep neural networks in NLP and the challenges involved in defending them.

Related Papers

• → Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives(2023)12 cited
• → On The Detection Of Adversarial Attacks Through Reliable AI(2022)2 cited
• ADVANCEMENT OF ATTACK AND DEFENSE TECHNIQUES IN ADVERSARIAL MACHINELEARNING(2020)
• → An Optimal Control View of Adversarial Machine Learning(2018)9 cited
• → Analyzing the Impact of Adversarial Examples on Explainable Machine Learning(2023)