Search

Shill attacks are a serious threat to the stability of filtering and recommendation systems. These attacks involve the injection of fake profiles into the system, which can compromise the reliability of system output. Several shilling attack detection techniques have been proposed, but they often have limitations in terms of accuracy. This works presents a enhanced method for detecting attacks in collaborative recommender systems. The proposed method is based on a combination of statistical and machine learning techniques. The statistical techniques are used to identify anomalous user behavior, while the machine learning techniques are used to classify users as either malicious or benign. The main contribution of the proposed method is the use of a hybrid approach that combines the strengths of statistical and machine learning techniques. The statistical techniques are able to identify anomalous user behavior that is not easily detected by machine learning techniques. The machine learning techniques are able to classify users as either malicious or benign with a high degree of accuracy. The proposed method was evaluated on a real-world dataset. The results showed that the proposed method was able to detect attacks with a high degree of accuracy. The proposed method uses a combination of ensemble learning and feature selection to achieve better accuracy than previous methods. The results of the experiments show that the proposed method can achieve an accuracy of up to 99%.

The stability and reliability of filtration and recommender systems are crucial for continuous operation. The presence of fake profiles, known as “shilling attacks,” can undermine the reliability of these systems. Therefore, it is important to detect and classify these attacks. Numerous techniques for detecting shilling attacks have been proposed, including supervised, semi-supervised, unsupervised, Deep Learning, and hyper deep learning methods. These techniques utilize well-known shilling attack models to target collaborative recommender systems. While previous research has focused on evaluating shilling attack strategies from a global perspective, considering factors such as attack size and attacker’s knowledge, there is a lack of comparative studies on the various existing and commonly used attack detection methods. This paper aims to fill this gap by providing a comprehensive survey of shilling attack models, detection attributes, and detection algorithms. Furthermore, we explore the traits of injected profiles that are exploited by detection algorithms, which has not been thoroughly investigated in prior works. We also conduct experimental studies on popular attack detection methods. Our experimental results reveal that hybrid deep learning algorithms exhibit the highest performance in shilling detection, followed by supervised learning algorithms and semi-supervised learning algorithms. In contrast, the unsupervised technique performs poorly. The deep learning-based Shilling Attack Detection demonstrates accuracy and quality in accurately identifying a variety of mixed attacks. This study provides valuable insights into shilling attack models, detection attributes, and detection algorithms. Our findings highlight the superior performance of hybrid deep learning algorithms in shilling detection, as well as the limitations of unsupervised techniques. Deep learning-based Shilling Attack Detection showcases its effectiveness and accuracy in identifying various types of attacks.

Highlights • Primary multi-criteria recommendation systems are highly vulnerable to manipulations. • Extension methods of shilling attacks against the multi-criteria domain are proposed. • A novel attack scheme is proposed for exploiting multi-criteria recommender systems. • Robustness analysis of multi-criteria recommendation algorithms is performed. Abstract Collaborative filtering is an emerging recommender system technique that aims guiding users based on other customers preferences with behavioral similarities. Such correspondences are located based on preference history of users. A relatively new extension of traditional collaborative filtering schemes takes into account not only how much a user likes an item, but also why she likes the item by collecting multi-criteria preferences focusing on distinctive features of the items. These multi-criteria collaborative filtering systems have the potential to improve recommender system accuracy since they reveal multiple views of users on products. However, due to providing more insightful recommendations, such systems might be subjected to malicious attacks more substantially than the traditional ones. Attackers attempt to insert fake profiles to bias outputs of these systems in favor of a particular product or disrepute the system itself. Since outputs of expert systems directly dependent on input signals; interventions to the inputs coherently cause failures on productions of such systems. In this study, we examine shilling attack strategies against multi-criteria preference collections, how to extend well-known attack scenarios against these systems, and propose an alternative attacking scheme. We analyze the robustness of baseline multi-criteria recommendation algorithms regarding various similarity aggregation procedures against proposed attacking schemes by the extensive experimental investigation. Empirical results on real-world data demonstrate that these systems are highly vulnerable to manipulations and proper attack detection practices are needed to ensure recommendation quality. According to our findings, manipulative attempts at such expert systems mislead decision-making process. [ABSTRACT FROM AUTHOR]

Online vendors employ collaborative filtering algorithms to provide recommendations to their customers so that they can increase their sales and profits. Although recommendation schemes are successful in e-commerce sites, they are vulnerable to shilling or profile injection attacks. On one hand, online shopping sites utilize collaborative filtering schemes to enhance their competitive edge over other companies. On the other hand, malicious users and/or competing vendors might decide to insert fake profiles into the user-item matrices in such a way so that they can affect the predicted ratings on behalf of their advantages. In the past decade, various studies have been conducted to scrutinize different shilling attacks strategies, profile injection attack types, shilling attack detection schemes, robust algorithms proposed to overcome such attacks, and evaluate them with respect to accuracy, cost/benefit, and overall performance. Due to their popularity and importance, we survey about shilling attacks in collaborative filtering algorithms. Giving an overall picture about various shilling attack types by introducing new classification attributes is imperative for further research. Explaining shilling attack detection schemes in detail and robust algorithms proposed so far might open a lead to develop new detection schemes and enhance such robust algorithms further, even propose new ones. Thus, we describe various attack types and introduce new dimensions for attack classification. Detailed description of the proposed detection and robust recommendation algorithms are given. Moreover, we briefly explain evaluation of the proposed schemes. We conclude the paper by discussing various open questions. [ABSTRACT FROM AUTHOR]

Privacy-preserving collaborative filtering schemes are becoming increasingly popular because they handle the information overload problem without jeopardizing privacy. However, they may be susceptible to shilling or profile injection attacks, similar to traditional recommender systems without privacy measures. Although researchers have proposed various privacy-preserving recommendation frameworks, it has not been shown that such schemes are resistant to profile injection attacks. In this study, we investigate two memory-based privacy-preserving collaborative filtering algorithms and analyze their robustness against several shilling attack strategies. We first design and apply formerly proposed shilling attack techniques to privately collected databases. We analyze their effectiveness in manipulating predicted recommendations by experimenting on real data-based benchmark data sets. We show that it is still possible to manipulate the predictions significantly on databases consisting of masked preferences even though a few of the attack strategies are not effective in a privacy-preserving environment. [ABSTRACT FROM AUTHOR]

Digital content production and distribution has radically changed our business models. An unprecedented volume of supply is now on offer, whetted by the demand of millions of users from all over the world. Since users cannot be expected to browse through millions of different items to find what they might like, filtering has become a popular technique to connect supply and demand: trusted users are first identified, and their opinions are then used to create recommendations. In this domain, users' trustworthiness has been measured according to one of the following two criteria: taste similarity (i.e., "I trust those who agree with me"), or social ties (i.e., "I trust my friends, and the people that my friends trust"). The former criterion aims at identifying concordant users, but is subject to abuse by malicious behaviors. The latter aims at detecting well-intentioned users, but fails to capture the natural subjectivity of tastes. In this article, we propose a new definition of trusted recommenders, addressing those users that are both well-intentioned and concordant. Based on this characterisation, we propose a novel approach to information filtering that we call dependable filtering.We describe alternative algorithms realizing this approach, and demonstrate, by means of extensive performance evaluation on a variety of real large-scale datasets, the high degree of both accuracy and robustness they entail. [ABSTRACT FROM AUTHOR]