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

End-to-end encryption (E2EE) by messaging platforms enable people to securelyand privately communicate with one another. Its widespread adoption howeverraised concerns that illegal content might now be shared undetected. Followingthe global pushback against key escrow systems, client-side scanning based onperceptual hashing has been recently proposed by tech companies, governmentsand researchers to detect illegal content in E2EE communications. We herepropose the first framework to evaluate the robustness of perceptualhashing-based client-side scanning to detection avoidance attacks and showcurrent systems to not be robust. More specifically, we propose threeadversarial attacks--a general black-box attack and two white-box attacks fordiscrete cosine transform-based algorithms--against perceptual hashingalgorithms. In a large-scale evaluation, we show perceptual hashing-basedclient-side scanning mechanisms to be highly vulnerable to detection avoidanceattacks in a black-box setting, with more than 99.9% of images successfullyattacked while preserving the content of the image. We furthermore show ourattack to generate diverse perturbations, strongly suggesting thatstraightforward mitigation strategies would be ineffective. Finally, we showthat the larger thresholds necessary to make the attack harder would probablyrequire more than one billion images to be flagged and decrypted daily, raisingstrong privacy concerns. Taken together, our results shed serious doubts on therobustness of perceptual hashing-based client-side scanning mechanismscurrently proposed by governments, organizations, and researchers around theworld.

Adversarial Detection Avoidance Attacks: Evaluating the robustness of perceptual hashing-based client-side scanning