Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems
As the use of recommender systems becomes generalized in society, the interest in varying the orientation of their recommendations is increasing. There are shilling attacks’ strategies that introduce malicious profiles in collaborative filtering recommender systems in order to promote the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8668763/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536174706917376 |
|---|---|
| author | Santiago Alonso Jesus Bobadilla Fernando Ortega Ricardo Moya |
| author_facet | Santiago Alonso Jesus Bobadilla Fernando Ortega Ricardo Moya |
| author_sort | Santiago Alonso |
| collection | DOAJ |
| description | As the use of recommender systems becomes generalized in society, the interest in varying the orientation of their recommendations is increasing. There are shilling attacks’ strategies that introduce malicious profiles in collaborative filtering recommender systems in order to promote the own products or services or to discredit those of the competition. Academic research against shilling attacks has been focused in statistical approaches to detect the unusual patterns in user ratings. Nowadays, there is a growing research area focused on the design of robust machine learning methods to neutralize the malicious profiles inserted into the system. This paper proposes an innovative robust method, based on matrix factorization, to neutralize the shilling attacks. Our method obtains the reliability value associated with each prediction of a user to an item. By monitoring the unusual reliability variations in the items prediction, we can avoid promoting the shilling predictions to the erroneous recommendations. This paper openly provides more than 13 000 individual experiments involving a wide range of attack strategies, both push, and nuke, in order to test the proposed approach. The results show that the proposed method is able to neutralize most of the existing attacks; its performance only decreases in the not relevant situations: when the attack size is not large enough to effectively affect the recommendations provided by the system. |
| format | Article |
| id | doaj-art-5b561dfb6415493bb49063db11186ae5 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5b561dfb6415493bb49063db11186ae52025-01-15T00:01:06ZengIEEEIEEE Access2169-35362019-01-017417824179810.1109/ACCESS.2019.29058628668763Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender SystemsSantiago Alonso0Jesus Bobadilla1https://orcid.org/0000-0003-0619-1322Fernando Ortega2https://orcid.org/0000-0003-4765-1479Ricardo Moya3Departamento Sistemas Informáticos, ETSI de Sistemas Informáticos, Universidad Politécnica de Madrid, Madrid, SpainDepartamento Sistemas Informáticos, ETSI de Sistemas Informáticos, Universidad Politécnica de Madrid, Madrid, SpainDepartamento Sistemas Informáticos, ETSI de Sistemas Informáticos, Universidad Politécnica de Madrid, Madrid, SpainTelefónica Investigación y Desarrollo, Madrid, SpainAs the use of recommender systems becomes generalized in society, the interest in varying the orientation of their recommendations is increasing. There are shilling attacks’ strategies that introduce malicious profiles in collaborative filtering recommender systems in order to promote the own products or services or to discredit those of the competition. Academic research against shilling attacks has been focused in statistical approaches to detect the unusual patterns in user ratings. Nowadays, there is a growing research area focused on the design of robust machine learning methods to neutralize the malicious profiles inserted into the system. This paper proposes an innovative robust method, based on matrix factorization, to neutralize the shilling attacks. Our method obtains the reliability value associated with each prediction of a user to an item. By monitoring the unusual reliability variations in the items prediction, we can avoid promoting the shilling predictions to the erroneous recommendations. This paper openly provides more than 13 000 individual experiments involving a wide range of attack strategies, both push, and nuke, in order to test the proposed approach. The results show that the proposed method is able to neutralize most of the existing attacks; its performance only decreases in the not relevant situations: when the attack size is not large enough to effectively affect the recommendations provided by the system.https://ieeexplore.ieee.org/document/8668763/Recommender systemsshilling attackscollaborative filteringreliabilitymalicious profilesmatrix factorization |
| spellingShingle | Santiago Alonso Jesus Bobadilla Fernando Ortega Ricardo Moya Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems IEEE Access Recommender systems shilling attacks collaborative filtering reliability malicious profiles matrix factorization |
| title | Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems |
| title_full | Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems |
| title_fullStr | Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems |
| title_full_unstemmed | Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems |
| title_short | Robust Model-Based Reliability Approach to Tackle Shilling Attacks in Collaborative Filtering Recommender Systems |
| title_sort | robust model based reliability approach to tackle shilling attacks in collaborative filtering recommender systems |
| topic | Recommender systems shilling attacks collaborative filtering reliability malicious profiles matrix factorization |
| url | https://ieeexplore.ieee.org/document/8668763/ |
| work_keys_str_mv | AT santiagoalonso robustmodelbasedreliabilityapproachtotackleshillingattacksincollaborativefilteringrecommendersystems AT jesusbobadilla robustmodelbasedreliabilityapproachtotackleshillingattacksincollaborativefilteringrecommendersystems AT fernandoortega robustmodelbasedreliabilityapproachtotackleshillingattacksincollaborativefilteringrecommendersystems AT ricardomoya robustmodelbasedreliabilityapproachtotackleshillingattacksincollaborativefilteringrecommendersystems |