Segment-Based Injection Attacks against Collaborative Filtering Recommender Systems

Burke, Robin; Mobasher, Bamshad; Bhaumik, Runa; Williams, Chad

doi:10.1109/icdm.2005.127

Cited by 69 publications

(78 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main aim of the attacker is to interact with the RS to build a large number of fake user profiles in the system with the target of affecting the system output i.e. either push (promote) or nuke (demote) a particular item [7]. Previous work done on has shown that if recommender systems of e-commerce are not protected from these attacks, there is a very high risk that the trust of customers in the site and predictions can be affected by the attacker.…”

Section: Introductionmentioning

confidence: 99%

Clustering Approach to detect Profile Injection Attacks in Recommender System

Kumar¹,

Garg²,

Rana³

2017

IJCA

View full text Add to dashboard Cite

Recommender systems apply techniques of knowledge discovery for specific problem to make personalized recommendation of the products or services to the users. The huge growth in the information and the count of visitors to the web sites especially on e-commerce in last few years creates some challenges for recommender systems. E-commerce recommender systems are vulnerable to the profile injection attacks, involving insertion of fake profiles into the system to influence the recommendations made to the users. Prior work has shown that performance of system can be affected by even small number of biased profiles. In this paper, we show that unsupervised clustering approach can be used effectively for the detection of profile injection attacks in recommender system. Here we give a comparative study of four clustering algorithms and measure their performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Clustering Approach to detect Profile Injection Attacks in Recommender System

Kumar¹,

Garg²,

Rana³

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Our prior work [2,3] identified a number of attack models, based on different assumptions about attacker knowledge and intent. The overall conclusion is that an attacker wishing to "push" a particular product (make it more likely to be recommended) or to "nuke" it (make it less likely to be recommended) can do so with a relatively modest number of injected profiles, with a minimum of system-specific knowledge and with only the kind of general knowledge about likely user ratings distribution that one might find by reading the newspaper.…”

Section: Introductionmentioning

confidence: 99%

Defending recommender systems: detection of profile injection attacks

Williams

Mobasher

Burke

2007

SOCA

139

105

View full text Add to dashboard Cite

Collaborative recommender systems are known to be highly vulnerable to profile injection attacks, attacks that involve the insertion of biased profiles into the ratings database for the purpose of altering the system's recommendation behavior. Prior work has shown when profiles are reverse engineered to maximize influence; even a small number of malicious profiles can significantly bias the system. This paper describes a classification approach to the problem of detecting and responding to profile injection attacks. A number of attributes are identified that distinguish characteristics present in attack profiles in general, as well as an attribute generation approach for detecting profiles based on reverse engineered attack models. Three well-known classification algorithms are then used to demonstrate the combined benefit of these attributes and the impact the selection of classifier has with respect to improving the robustness of the recommender system. Our study demonstrates this technique significantly reduces the impact of the most powerful attack models previously studied, particularly when combined with a support vector machine classifier.

show abstract

“…These types of attack have been extensively studied as shilling attacks or profile injection attacks. According to such attacks usually involve setting up dummy profiles, and assume different amounts of knowledge about the system [58].…”

Section: The Challenges and Limitations Of Recommendation Systemsmentioning

confidence: 99%

A Literature Review of Empirical Studies of Recommendation Systems

Akhtar¹,

Agarwal²

2015

IJAIS

View full text Add to dashboard Cite

In the last twelve years, the number of web user increases, so intensely leading to intense advancement in web services which leads to enlargement the usage data at higher rates. The purpose of a recommender System is to generate meaningful recommendations to a collection of users for items or products that might interest them. Recommender systems differ in the way they analyze these data sources to develop notions of congeniality between users and items which can be used to identify well-matched pairs. The recommender system technology intentions to help users in finding items that match their personal interests. It has a successful usage in ecommerce applications to deal with problems related to information overload proficiently. In this paper, we will extensively present a survey of six existing recommendation system. The Collaborative Filtering systems analyze historical interactions alone, while Content-Based Filtering systems are based on profile attributes, Hybrid Techniques attempt to combine both of these designs, Demographic Based Recommender systems aim to categorize the user based on personal attributes and make recommendations based on demographic classes, while Knowledge-Based Recommendation attempts to suggest objects based on inferences about a user's needs and preferences, and UtilityBased Recommender systems make recommendations based on the computation of the utility of each item for the user. In this paper, we have recognized 60 research papers on recommender systems, which were published between 1971 and 2014. Finally, few research papers had an influence on research paper recommender systems in practice. We also recognized a lack of authority and long term research interest in the field, 78% of the authors published no more than one paper on research paper recommender systems, and there was miniature cooperation among different co-author groups.

show abstract

Segment-Based Injection Attacks against Collaborative Filtering Recommender Systems

Cited by 69 publications

References 5 publications

Clustering Approach to detect Profile Injection Attacks in Recommender System

Clustering Approach to detect Profile Injection Attacks in Recommender System

Defending recommender systems: detection of profile injection attacks

A Literature Review of Empirical Studies of Recommendation Systems

Contact Info

Product

Resources

About