DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising
Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be exploited with carefully crafted adversarial texts. Inspired by the ability of diffusion models to predict and reduce noise in computer vision, we propose a novel and flexible adversarial defense method for language classification tasks, DiffuseDef, which incorporates a diffusion layer as a denoiser between the encoder and the classifier. The diffusion layer is trained on top of the existing classifier, ensuring seamless integration with any model in a plug-and-play manner. During inference, the adversarial hidden state is first combined with sampled noise, then denoised iteratively and finally ensembled to produce a robust text representation. By integrating adversarial training, denoising, and ensembling techniques, we show that DiffuseDef improves over existing adversarial defense methods and achieves state-of-the-art performance against common black-box and white-box adversarial attacks.
Code (1)
Tasks
Adversarial DefenseDenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Boosting Adversarial Attacks on Neural Networks with Better Optimizer
Convolutional neural networks have outperformed humans in image recognition tasks, but they remain vulnerable to attacks from adversarial examples. Since these data are crafted by adding imperceptible noise to normal ima…
Binary Iterative Method for Non-targeted Adversarial Attack
Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models. Since adver…
Adversarial RobustnessAdversarial AttackCascade Adversarial Machine Learning Regularized with a Unified Embedding
Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively …
BIG-bench Machine LearningExploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
We investigate to what extent alternative variants of Artificial Neural Networks (ANNs) are susceptible to adversarial attacks. We analyse the adversarial robustness of conventional, stochastic ANNs and Spiking Neural Ne…
Adversarial RobustnessArchitectural Adversarial Robustness: The Case for Deep Pursuit
Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood,…
Adversarial Robustnessglobal-optimization