A detection method for hybrid attacks in recommender systems

Hao, Yaojun; Meng, Gang; Wang, Jian; Zong, Chunmei

doi:10.1016/j.is.2022.102154

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their study, Hao et al (2023) introduced an innovative method for identifying hybrid assaults in recommender systems. Conventional detection approaches frequently encounter difficulties in recognizing these attacks, which involve a combination of model-generative shilling attacks and group shilling attacks.…”

Section: Related Workmentioning

confidence: 99%

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

Gunes

2024

PeerJ Computer Science

View full text Add to dashboard Cite

The topic of privacy-preserving collaborative filtering is gaining more and more attention. Nevertheless, privacy-preserving collaborative filtering techniques are vulnerable to shilling or profile injection assaults. Hence, it is crucial to identify counterfeit profiles in order to achieve total success. Various techniques have been devised to identify and prevent intrusion patterns from infiltrating the system. Nevertheless, these strategies are specifically designed for collaborative filtering algorithms that do not prioritize privacy. There is a scarcity of research on identifying shilling attacks in recommender systems that prioritize privacy. This work presents a novel technique for identifying shilling assaults in privacy-preserving collaborative filtering systems. We employ an ant colony clustering detection method to effectively identify and eliminate fake profiles that are created by six widely recognized shilling attacks on compromised data. The objective of the study is to categorize the fraudulent profiles into a specific cluster and separate this cluster from the system. Empirical experiments are conducted with actual data. The empirical findings demonstrate that the strategy derived from the study effectively eliminates fraudulent profiles in privacy-preserving collaborative filtering.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Gunes

2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Another study is performed by Reference 37 which propose a framework to identify anomalous rating profiles. Reference 38 proposes a detector based on the graph convolutional networks to simultaneously detect hybrid attacks. Reference 39 presents a shilling attack detection system in which they can not only identify individual shillers but also group shillers.…”

Section: Related Workmentioning

confidence: 99%

A novel classification‐based shilling attack detection approach for multi‐criteria recommender systems

Kaya

Yalçin

Kaleli

2023

Computational Intelligence

View full text Add to dashboard Cite

Recommender systems are emerging techniques guiding individuals with provided referrals by considering their past rating behaviors. By collecting multi-criteria preferences concentrating on distinguishing perspectives of the items, a new extension of traditional recommenders, multi-criteria recommender systems reveal how much a user likes an item and why user likes it; thus, they can improve predictive accuracy. However, these systems might be more vulnerable to malicious attacks than traditional ones, as they expose multiple dimensions of user opinions on items. Attackers might try to inject fake profiles into these systems to skew the recommendation results in favor of some particular items or to bring the system into discredit. Although several methods exist to defend systems against such attacks for traditional recommenders, achieving robust systems by capturing shill profiles remains elusive for multi-criteria rating-based ones. Therefore, in this study, we first consider a prominent and novel attack type, that is, the power-item attack model, and introduce its four distinct variants adapted for multi-criteria data collections. Then, we propose a classification method detecting shill profiles based on various generic and model-based user attributes, most of which are new features usually related to item popularity and distribution of rating values. The experiments conducted on three benchmark datasets conclude that

show abstract

“…In group attack detection, Wu et al [25] constructed features from multiple data sources for group attack detection, which performs well on synthetic datasets. Wu [26,27] detected group attacks by building a graph neural network attack detection model and a semisupervised model based on clustering and graph convolutional networks. Tese methods exhibit good timeliness in detecting mixed attacks.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Forest-Based E-Commerce Recommendation Attack Detection Model

Mingxun,

Jiewu,

Zhigang

et al. 2023

Security and Communication Networks

View full text Add to dashboard Cite

With the advancement of Internet, recommendation systems have become an indispensable component for every e-commerce platform, playing an increasingly pivotal role in product recommendations. However, due to the recommendation mechanisms of these systems, numerous new attack patterns have emerged. A novel attack pattern targeting e-commerce recommendation systems, termed the “Ride Item’s Coattails” attack, fabricates false click information to deceitfully establish associations between popular products and low-quality products, intending to mislead the e-commerce platform’s recommendation system and promote the sales of substandard products. This article presents a recommendation system attack detection method based on the Deep Forest algorithm to address the challenges of these novel recommendation system attacks. Random forests are used for feature selection, aiming to filter crucial features and reduce feature redundancy. To tackle the issue of extreme class imbalance, a symmetric sampling technique based on k-means centroids is introduced. This approach addresses the incomplete noise filtering and sampling data comprehensiveness issues commonly found in undersampling algorithms. Considering the potential for even more imbalanced data in real-world scenarios, a combined strategy of undersampling and SMOTE resampling is used to handle imbalanced data. The proposed algorithm was trained on e-commerce “Ride Item’s Coattails” attack identification data from Alibaba Cloud’s Tianchi, which originates from genuine recommendation system attack data. The proposed method was compared with various deep learning and machine learning algorithms, such as DLMP and deep neural networks (DNN), for extensive validation. Experiments demonstrate that the proposed technique effectively meets the demands for attack detection.

show abstract

A detection method for hybrid attacks in recommender systems

Cited by 5 publications

References 17 publications

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

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

A novel classification‐based shilling attack detection approach for multi‐criteria recommender systems

Deep Forest-Based E-Commerce Recommendation Attack Detection Model

Contact Info

Product

Resources

About