paper-with-me

Papers

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising

2024-06-28 · Zhenhao Li, Huichi Zhou, Marek Rei, Lucia Specia

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.

📄 PDF Abstract BibTeX arXiv:2407.00248

Code (1)

nickeilf/diffusedef 공식 구현 pytorch

Tasks

Adversarial DefenseDenoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Boosting Adversarial Attacks on Neural Networks with Better Optimizer

2020-12-01 · Heng Yin, Hengwei Zhang, Jindong Wang, Ruiyu Dou

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

2026-07-05 · Naman Goyal, Milan Chaudhari arxiv

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 Attack

Cascade Adversarial Machine Learning Regularized with a Unified Embedding

2017-08-08 · ICLR 2018 1 · Taesik Na, Jong Hwan Ko, Saibal Mukhopadhyay

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 Learning

Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks

2019-12-08 · Yi Xiang Marcus Tan, Yuval Elovici, Alexander Binder

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 Robustness

Architectural Adversarial Robustness: The Case for Deep Pursuit

2020-11-29 · CVPR 2021 1 · George Cazenavette, Calvin Murdock, Simon Lucey

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