Guardado en:
Detalles Bibliográficos
Autor principal: Wang, Yongyu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.10850
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912760493768704
author Wang, Yongyu
author_facet Wang, Yongyu
contents User based collaborative filtering (CF) relies on a user and user similarity graph, making it vulnerable to profile injection (shilling) attacks that manipulate neighborhood relations to promote (push) or demote (nuke) target items. In this work, we propose an adversarial robustness based edge reweighting defense for CF. We first assign each user and user edge a non robustness score via spectral adversarial robustness evaluation, which quantifies the edge sensitivity to adversarial perturbations. We then attenuate the influence of non robust edges by reweighting similarities during prediction. Extensive experiments demonstrate that the proposed method effectively defends against various types of attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Defending Collaborative Filtering Recommenders via Adversarial Robustness Based Edge Reweighting
Wang, Yongyu
Machine Learning
User based collaborative filtering (CF) relies on a user and user similarity graph, making it vulnerable to profile injection (shilling) attacks that manipulate neighborhood relations to promote (push) or demote (nuke) target items. In this work, we propose an adversarial robustness based edge reweighting defense for CF. We first assign each user and user edge a non robustness score via spectral adversarial robustness evaluation, which quantifies the edge sensitivity to adversarial perturbations. We then attenuate the influence of non robust edges by reweighting similarities during prediction. Extensive experiments demonstrate that the proposed method effectively defends against various types of attacks.
title Defending Collaborative Filtering Recommenders via Adversarial Robustness Based Edge Reweighting
topic Machine Learning
url https://arxiv.org/abs/2412.10850