What question did this study set out to answer?

To develop a sophisticated model, MDM-GANSA, for generating realistic fake user profiles in shilling attacks on recommender systems.

January 14, 2026InformationOpen Access

MDM-GANSA: A Multi-Distribution Generative Shilling Attack for Recommender Systems

View Full Paper

Ask AI

Bookmark

Authors

Proposed model employs autoencoder for data-driven dependency modeling, enhancing the realism of fake profiles.

To develop a sophisticated model, MDM-GANSA, for generating realistic fake user profiles in shilling attacks on recommender systems.
Introduces dynamic adaptive noise strategy with a weight predictor network.
Utilizes an autoencoder for data-driven dependency modeling.
Implements a two-stage generative architecture with fine-grained loss constraints.
MDM-GANSA significantly outperforms baseline models in attack effectiveness and stealthiness.
Demonstrates improved realism in generated fake user profiles.

Zhou et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

January 14, 2026InformationOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Proposed model employs autoencoder for data-driven dependency modeling, enhancing the realism of fake profiles.

To develop a sophisticated model, MDM-GANSA, for generating realistic fake user profiles in shilling attacks on recommender systems.
Introduces dynamic adaptive noise strategy with a weight predictor network.
Utilizes an autoencoder for data-driven dependency modeling.
Implements a two-stage generative architecture with fine-grained loss constraints.
MDM-GANSA significantly outperforms baseline models in attack effectiveness and stealthiness.
Demonstrates improved realism in generated fake user profiles.

Zhou et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark