Do we need entire training data for adversarial training?
원문 초록
Deep Neural Networks (DNNs) are being used to solve a wide range of problems in many domains including safety-critical domains like self-driving cars and medical imagery. DNNs suffer from vulnerability against adversarial attacks. In the past few years, numerous approaches have been proposed to tackle this problem by training networks using adversarial training. Almost all the approaches generate adversarial examples for the entire training dataset, thus increasing the training time drastically. We show that we can decrease the training time for any adversarial training algorithm by using only a subset of training data for adversarial training. To select the subset, we filter the adversarially-prone samples from the training data. We perform a simple adversarial attack on all training examples to filter this subset. In this attack, we add a small perturbation to each pixel and a few grid lines to the input image. We perform adversarial training on the adversarially-prone subset and mix it with vanilla training performed on the entire dataset. Our results show that when our method-agnostic approach is plugged into FGSM, we achieve a speedup of 3.52x on MNIST and 1.98x on the CIFAR-10 dataset with comparable robust accuracy. We also test our approach on state-of-the-art Free adversarial training and achieve a speedup of 1.2x in training time with a marginal drop in robust accuracy on the ImageNet dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF Infeasible
ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
토론
이 논문과 연결된 포럼 글이 아직 없습니다.