← Back to the feed
AI & softwareResearch findings

A Structure-Aware Fairness Attack Method for Recommender Systems

Original published 2026.06.28 04:50 KSTAdded to Blackdeck 2026.10.20 12:16 KST

What has changed?

Proposes a reinforcement learning-based method that considers both structural and sequential dependencies to worsen fairness

Key points

  1. Unfairness in recommender systems has raised significant social and ethical concerns
  2. Existing research has focused on performance degradation rather than fairness degradation
  3. The proposed method enhances unfairness by modeling structural and sequential dependencies in fake interactions

Connect it to your work

Models structural and sequential patterns of fake user-item interactions to amplify bias in recommendation systems

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivFairness Attacks on Recommender Systems