Attack detection in recommender systems based on target item analysis

@article{Zhou2014AttackDI,
  title={Attack detection in recommender systems based on target item analysis},
  author={Wei Zhou and Junhao Wen and Yun Sing Koh and Shafiq Alam and Gillian Dobbie},
  journal={2014 International Joint Conference on Neural Networks (IJCNN)},
  year={2014},
  pages={332-339}
}
Recommender systems are highly vulnerable to attacks. Attackers who introduce biased ratings in order to affect recommendations, have been shown to be effective against collaborative filtering algorithms. In this paper, we study the use of statistical metrics to detect rating patterns of attackers. Two metrics, Rating Deviation from Mean Agreement (RDMA… CONTINUE READING