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 are vulnerable to universal adversarial perturbation(UAP), an instance-agnostic perturbation capable of fooling the target modelfor most samples. Compared to instance-specific adversarial examples, UAP ismore challenging as it needs to generalize across various samples and models.In this paper, we examine the serious dilemma of UAP generation methods from ageneralization perspective -- the gradient vanishing problem using small-batchstochastic gradient optimization and the local optima problem using large-batchoptimization. To address these problems, we propose a simple and effectivemethod called Stochastic Gradient Aggregation (SGA), which alleviates thegradient vanishing and escapes from poor local optima at the same time.Specifically, SGA employs the small-batch training to perform multipleiterations of inner pre-search. Then, all the inner gradients are aggregated asa one-step gradient estimation to enhance the gradient stability and reducequantization errors. Extensive experiments on the standard ImageNet datasetdemonstrate that our method significantly enhances the generalization abilityof UAP and outperforms other state-of-the-art methods. The code is available athttps://github.com/liuxuannan/Stochastic-Gradient-Aggregation.

Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation