English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep neural networks have been successfully applied in various machinelearning tasks. However, studies show that neural networks are susceptible toadversarial attacks. This exposes a potential threat to neural network-basedintelligent systems. We observe that the probability of the correct resultoutputted by the neural network increases by applying small first-orderperturbations generated for non-predicted class labels to adversarial examples.Based on this observation, we propose a method for counteracting adversarialperturbations to improve adversarial robustness. In the proposed method, werandomly select a number of class labels and generate small first-orderperturbations for these selected labels. The generated perturbations are addedtogether and then clamped onto a specified space. The obtained perturbation isfinally added to the adversarial example to counteract the adversarialperturbation contained in the example. The proposed method is applied atinference time and does not require retraining or finetuning the model. Weexperimentally validate the proposed method on CIFAR-10 and CIFAR-100. Theresults demonstrate that our method effectively improves the defenseperformance of several transformation-based defense methods, especially againststrong adversarial examples generated using more iterations.

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations