Collaborative filtering recommendation using fusing criteria against shilling attacks
The collaborative filtering recommendation technique (CFR) is one of the techniques used in recommended systems, in which the most proximal neighbours to a target user are selected. Their profiles are used to predict rating for items as yet unrated by that target user. However, malicious users injec...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2022.2078280 |
| _version_ | 1797684044258869248 |
|---|---|
| author | Li Li Zhongqun Wang Chen Li Linjun Chen Yong Wang |
| author_facet | Li Li Zhongqun Wang Chen Li Linjun Chen Yong Wang |
| author_sort | Li Li |
| collection | DOAJ |
| description | The collaborative filtering recommendation technique (CFR) is one of the techniques used in recommended systems, in which the most proximal neighbours to a target user are selected. Their profiles are used to predict rating for items as yet unrated by that target user. However, malicious users inject fake user profiles to destroy the security and reliability of the recommender systems, which is called shilling attacks. Therefore, it is crucial to improve the recommendation technique against shilling attacks. Malicious users use a single method to perform shilling attacks. Intuitively, fusing multiple criteria to construct CFR can effectively resist shilling attacks. A novel CFR is proposed against shilling attacks (called CFR-F). In our approach, a similar interest users’ resource set is obtained first by integrating users’ dynamic interest model and social tags. Then, a similar interest user resource set is selected according to a strategy that selects preference influence weight based on user background. Our experimental results show that our approach can recommend accurate information resources and has a lower Mean Absolute Error (MAE) and Average Prediction Shift (APS) than traditional techniques by 50% and 20%, respectively. |
| first_indexed | 2024-03-12T00:23:41Z |
| format | Article |
| id | doaj.art-00cab4bbc82c43bb8f115686e01ced5a |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:23:41Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-00cab4bbc82c43bb8f115686e01ced5a2023-09-15T10:48:00ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013411678169610.1080/09540091.2022.20782802078280Collaborative filtering recommendation using fusing criteria against shilling attacksLi Li0Zhongqun Wang1Chen Li2Linjun Chen3Yong Wang4Library, Anhui Polytechnic UniversityLibrary, Anhui Polytechnic UniversityLibrary, Anhui Polytechnic UniversitySchool of Computer and Information, Anhui Polytechnic UniversitySchool of Computer and Information, Anhui Polytechnic UniversityThe collaborative filtering recommendation technique (CFR) is one of the techniques used in recommended systems, in which the most proximal neighbours to a target user are selected. Their profiles are used to predict rating for items as yet unrated by that target user. However, malicious users inject fake user profiles to destroy the security and reliability of the recommender systems, which is called shilling attacks. Therefore, it is crucial to improve the recommendation technique against shilling attacks. Malicious users use a single method to perform shilling attacks. Intuitively, fusing multiple criteria to construct CFR can effectively resist shilling attacks. A novel CFR is proposed against shilling attacks (called CFR-F). In our approach, a similar interest users’ resource set is obtained first by integrating users’ dynamic interest model and social tags. Then, a similar interest user resource set is selected according to a strategy that selects preference influence weight based on user background. Our experimental results show that our approach can recommend accurate information resources and has a lower Mean Absolute Error (MAE) and Average Prediction Shift (APS) than traditional techniques by 50% and 20%, respectively.http://dx.doi.org/10.1080/09540091.2022.2078280shilling attackuser contextdynamic social behavioursocial tags |
| spellingShingle | Li Li Zhongqun Wang Chen Li Linjun Chen Yong Wang Collaborative filtering recommendation using fusing criteria against shilling attacks Connection Science shilling attack user context dynamic social behaviour social tags |
| title | Collaborative filtering recommendation using fusing criteria against shilling attacks |
| title_full | Collaborative filtering recommendation using fusing criteria against shilling attacks |
| title_fullStr | Collaborative filtering recommendation using fusing criteria against shilling attacks |
| title_full_unstemmed | Collaborative filtering recommendation using fusing criteria against shilling attacks |
| title_short | Collaborative filtering recommendation using fusing criteria against shilling attacks |
| title_sort | collaborative filtering recommendation using fusing criteria against shilling attacks |
| topic | shilling attack user context dynamic social behaviour social tags |
| url | http://dx.doi.org/10.1080/09540091.2022.2078280 |
| work_keys_str_mv | AT lili collaborativefilteringrecommendationusingfusingcriteriaagainstshillingattacks AT zhongqunwang collaborativefilteringrecommendationusingfusingcriteriaagainstshillingattacks AT chenli collaborativefilteringrecommendationusingfusingcriteriaagainstshillingattacks AT linjunchen collaborativefilteringrecommendationusingfusingcriteriaagainstshillingattacks AT yongwang collaborativefilteringrecommendationusingfusingcriteriaagainstshillingattacks |