AuxBlocks: Defense Adversarial Example via Auxiliary Blocks
Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications. However, recent studies observe gradient-masking defenses are self-deceiving methods if an attacker can realize this defense. In this paper, we propose a new defense method based on appending information. We introduce the Aux Block model to produce extra outputs as a self-ensemble algorithm and analytically investigate the robustness mechanism of Aux Block. We have empirically studied the efficiency of our method against adversarial examples in two types of white-box attacks, and found that even in the full white-box attack where an adversary can craft malicious examples from defense models, our method has a more robust performance of about 54.6% precision on Cifar10 dataset and 38.7% precision on Mini-Imagenet dataset. Another advantage of our method is that it is able to maintain the prediction accuracy of the classification model on clean images, and thereby exhibits its high potential in practical applications
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples
Adversarial examples reveal the vulnerability and unexplained nature of neural networks. Studying the defense of adversarial examples is of considerable practical importance. Most adversarial examples that misclassify ne…
Automated Discovery of Adaptive Attacks on Adversarial Defenses
Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks,…
Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Intermediate Feature Distance
Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, which pose security challenges to hyperspectral image (HSI) classification technologies based on DNNs. In the domain of natural images, numerous transfer…
Adversarial AttackHyperspectral Image Classificationimage-classificationImage ClassificationConstructing Unrestricted Adversarial Examples with Generative Models
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose u…
Generative Adversarial NetworkAID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense
We propose an AID-purifier that can boost the robustness of adversarially-trained networks by purifying their inputs. AID-purifier is an auxiliary network that works as an add-on to an already trained main classifier. To…
Adversarial Defense