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 achieved unprecedented success on diverse visiontasks. However, they are vulnerable to adversarial noise that is imperceptibleto humans. This phenomenon negatively affects their deployment in real-worldscenarios, especially security-related ones. To evaluate the robustness of atarget model in practice, transfer-based attacks craft adversarial samples witha local model and have attracted increasing attention from researchers due totheir high efficiency. The state-of-the-art transfer-based attacks aregenerally based on data augmentation, which typically augments multipletraining images from a linear path when learning adversarial samples. However,such methods selected the image augmentation path heuristically and may augmentimages that are semantics-inconsistent with the target images, which harms thetransferability of the generated adversarial samples. To overcome the pitfall,we propose the Path-Augmented Method (PAM). Specifically, PAM first constructsa candidate augmentation path pool. It then settles the employed augmentationpaths during adversarial sample generation with greedy search. Furthermore, toavoid augmenting semantics-inconsistent images, we train a Semantics Predictor(SP) to constrain the length of the augmentation path. Extensive experimentsconfirm that PAM can achieve an improvement of over 4.8% on average comparedwith the state-of-the-art baselines in terms of the attack success rates.

Improving the Transferability of Adversarial Samples by Path-Augmented Method