Effective Attack Models for Shilling Item-Based Collaborative Filtering Systems

125 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Data Poisoning Attacks on Factorization-Based Collaborative Filtering (2016, background): “L G ] 5 systems and their reliance on user-specified judgments for building profiles, various forms of attacks are possible and have been discussed, such as the random attack and random product push/nuke attack [4, 5].”
Recommender Systems (2016, unknown): “The bandwagon attack works effectively for user-user collaborative filtering algorithms, but it is not quite as effective for item-based algorithms [246, 329, 445].”
Shilling attacks against recommender systems: a comprehensive survey (2012, background): “Mobasher et al. (2006b) study the robustness of model-based CF schemes with respect to shilling attacks because memory-based algorithms have been shown to be vulnerable to profile injection attacks.”