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

Vertical federated learning (VFL) system has recently become prominent as aconcept to process data distributed across many individual sources without theneed to centralize it. Multiple participants collaboratively train models basedon their local data in a privacy-aware manner. To date, VFL has become a defacto solution to securely learn a model among organizations, allowingknowledge to be shared without compromising privacy of any individuals. Despitethe prosperous development of VFL systems, we find that certain inputs of aparticipant, named adversarial dominating inputs (ADIs), can dominate the jointinference towards the direction of the adversary's will and force other(victim) participants to make negligible contributions, losing rewards that areusually offered regarding the importance of their contributions in federatedlearning scenarios. We conduct a systematic study on ADIs by first provingtheir existence in typical VFL systems. We then propose gradient-based methodsto synthesize ADIs of various formats and exploit common VFL systems. Wefurther launch greybox fuzz testing, guided by the saliency score of ``victim''participants, to perturb adversary-controlled inputs and systematically explorethe VFL attack surface in a privacy-preserving manner. We conduct an in-depthstudy on the influence of critical parameters and settings in synthesizingADIs. Our study reveals new VFL attack opportunities, promoting theidentification of unknown threats before breaches and building more secure VFLsystems.

ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems