ToDA: Target-oriented Diffusion Attacker against Recommendation System
Xiaohao Liu, Zhulin Tao, Ting Jiang, He Chang, Yunshan Ma, Yinwei Wei,, Xiang Wang

TL;DR
This paper introduces ToDA, a novel diffusion-based attack method against recommendation systems, leveraging latent diffusion models to craft targeted malicious user profiles with improved stability and effectiveness.
Contribution
The paper pioneers the use of diffusion models for shilling attacks on recommendation systems, proposing a new framework that outperforms existing generative attack methods.
Findings
ToDA achieves higher attack success rates than baselines.
The diffusion-based approach provides more stable and targeted profile generation.
Extensive experiments validate the effectiveness of ToDA against state-of-the-art defenses.
Abstract
Recommendation systems (RS) have become indispensable tools for web services to address information overload, thus enhancing user experiences and bolstering platforms' revenues. However, with their increasing ubiquity, security concerns have also emerged. As the public accessibility of RS, they are susceptible to specific malicious attacks where adversaries can manipulate user profiles, leading to biased recommendations. Recent research often integrates additional modules using generative models to craft these deceptive user profiles, ensuring them are imperceptible while causing the intended harm. Albeit their efficacy, these models face challenges of unstable training and the exploration-exploitation dilemma, which can lead to suboptimal results. In this paper, we pioneer to investigate the potential of diffusion models (DMs), for shilling attacks. Specifically, we propose a novel…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMental Health via Writing · Sentiment Analysis and Opinion Mining · Machine Learning in Healthcare
