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

Adversarial attacks against deep learning-based object detectors have beenstudied extensively in the past few years. Most of the attacks proposed havetargeted the model's integrity (i.e., caused the model to make incorrectpredictions), while adversarial attacks targeting the model's availability, acritical aspect in safety-critical domains such as autonomous driving, have notyet been explored by the machine learning research community. In this paper, wepropose a novel attack that negatively affects the decision latency of anend-to-end object detection pipeline. We craft a universal adversarialperturbation (UAP) that targets a widely used technique integrated in manyobject detector pipelines -- non-maximum suppression (NMS). Our experimentsdemonstrate the proposed UAP's ability to increase the processing time ofindividual frames by adding "phantom" objects that overload the NMS algorithmwhile preserving the detection of the original objects which allows the attackto go undetected for a longer period of time.

Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors