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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

An adversarial patch can arbitrarily manipulate image pixels within arestricted region to induce model misclassification. The threat of thislocalized attack has gained significant attention because the adversary canmount a physically-realizable attack by attaching patches to the victim object.Recent provably robust defenses generally follow the PatchGuard framework byusing CNNs with small receptive fields and secure feature aggregation forrobust model predictions. In this paper, we extend PatchGuard to PatchGuard++for provably detecting the adversarial patch attack to boost both provablerobust accuracy and clean accuracy. In PatchGuard++, we first use a CNN withsmall receptive fields for feature extraction so that the number of featurescorrupted by the adversarial patch is bounded. Next, we apply masks in thefeature space and evaluate predictions on all possible masked feature maps.Finally, we extract a pattern from all masked predictions to catch theadversarial patch attack. We evaluate PatchGuard++ on ImageNette (a 10-classsubset of ImageNet), ImageNet, and CIFAR-10 and demonstrate that PatchGuard++significantly improves the provable robustness and clean performance.

PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches