Work

Balancing Imperceptible and Aggressive Poisoning Attack for Recommender Systems: A Simple Multinomial Diffusion Model

Year: 2026

Type: article

Abstract: Online platforms’ openness makes Recommender Systems (RSs) susceptible to data poisoning attacks, where malicious user profiles are injected into the training dataset to distort recommendation outcomes. However, existing poisoning attack methods often struggle to achieve an optimal effectiveness on both imperceptibility and aggressiveness. To address this issue, we propose a novel poisoning attack method for RSs, named MDPAttack, which consists of three key modules, each focusing on imperceptibility and aggressiveness. Specifically, we first train a Multinomial Diffusion Model (MDM) to model discrete rating data, effectively minimizing information loss during data processing and thereby enhancing the imperceptibility of the generated profiles. Then, we combine the influence function with the Fast Gradient Sign Method (FGSM) to iteratively improve the aggressiveness of poisoning profiles by leveraging template profiles. Finally, these two properties are seamlessly integrated within the MDPAttack framework. Extensive experiments on both classic and modern deep learning-based RSs demonstrate that MDPAttack generates highly imperceptible profiles while maintaining attack performance comparable to state-of-the-art methods.

Source: ACM Transactions on Information Systems

DOI: 10.1145/3797026

Authors: Jun Zhu, Yuanchun Jiang, Yidong Chai, Yang Qian, Yang Wang

Institutions: Hefei University of Technology, City University of Hong Kong, City University of Hong Kong (Dongguan)

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Award: G6722437174