Privacy-Aware Detection of Shilling Profiles on Arbitrarily Distributed Recommender Systems

Abstract

Due to the mutual advantage of small-scale online service providers, they need to collaborate to deliver recommendations based on arbitrarily distributed preference data without jeopardizing their confidentiality. Besides privacy issues, parties also have concerns regarding the vulnerability against recommendation manipulation attempts, referred to as shilling attacks. Although there are methods for detecting these injected malicious profiles in central server-based configurations, they are not readily suitable for employing arbitrarily distributed data. In this paper, we present a novel classification-based shilling attack detection protocol enabling the recognition of malicious profiles in arbitrarily distributed configurations without compromising the privacy of collaborating parties. The analysis of the proposed protocol regarding confidentiality of parties reveals that the process is bound to collaboration by design, which does not allow parties to achieve detection by themselves. Furthermore, empirical evaluations using real-world preference data demonstrate that the protocol can achieve significantly high detection rates facilitating privacy-aware data collaboration.

A novel clustered-based detection method for shilling attack in private environments

“…In summary, they provided valuable perspectives on identifying shilling assaults in privacy-preserving collaborative filtering systems. Yilmazel, Bilge & Kaleli (2019) introduced a new strategy for detecting shilling attacks in recommender systems that are disseminated in an arbitrary manner. The protocol is based on categorization.…”

“…The approach relies on a bisecting k-means clustering technique, in which attack profiles are gathered within a leaf node of a binary decision tree. Yilmazel, Bilge & Kaleli (2019) introduced a new strategy for detecting shilling attacks in recommender systems that are disseminated in an arbitrary manner. The protocol is based on categorization, facilitating the identification of malevolent profiles while safeguarding the privacy of the parties involved in collaboration.…”

Blockchain Based Privacy Preserving Recommendation System (BPPRS) Using Digital Signatures

“…A typical fraud is conducted by creating dummy profiles to manipulate the desirability of items and products. [5] Proposed a unique classification based shilling attack detection protocol in which the unauthorized profiles in arbitrarily distributed configurations are analysed without compromising the privacy of collaborating parties. [11]proposed a Blockchain based authentication key exchange protocol which is based on one-way hash function.…”