Assessing and Enhancing Adversarial Robustness for Review-Based Recommender System: A Design Science Approach

Authors

Ruicheng Liang, Hefei University of TechnologyFollow
Yidong Chai, Hefei University of TechnologyFollow
Weifeng Li, University of GeorgiaFollow
Michael Chau, The University of Hong KongFollow
Yuanchun Jiang, School of Management, Hefei University of TechnologyFollow
Yezheng Liu, School of Management, Hefei University of TechnologyFollow

Abstract

Whereas recommender system (RS) is ubiquitous in e-commerce platforms, recent years have seen grievous adversarial attacks on RS. However, no prior studies have evaluated RS’s adversarial vulnerability of utilizing online reviews. In this work, we follow the guidelines of adversarial robustness theory and adopt computational design science paradigm to design a novel “Min-Max” problem-based framework for assessing and enhancing adversarial robustness of review-based RS (R-RS). The framework includes an assessment component called Anchor Imitator (AIM) for crafting adversarial samples, and three enhancement components for copying with adversarial vulnerability, involving stochastic recommending process (SRP) that increases the difficulty of obtaining model information, weighted input dropout (WID) that reduces sensitivity on sensitive words, and weighted adversarial contrastive learning (WACL) that learns robust feature. We evaluate the devised framework on ground truth datasets, results demonstrate that R-RS is vulnerable to adversarial attack and the enhancement components significantly improve the adversarial robustness of R-RS.

Comments

Paper Number 1793; Track AI; Complete Paper

Recommended Citation

Liang, Ruicheng; Chai, Yidong; Li, Weifeng; Chau, Michael; Jiang, Yuanchun; and Liu, Yezheng, "Assessing and Enhancing Adversarial Robustness for Review-Based Recommender System: A Design Science Approach" (2023). PACIS 2023 Proceedings. 211.
https://aisel.aisnet.org/pacis2023/211