Name
Abstract | ||
|---|---|---|
Recommender systems using Collaborative Filtering techniques are capable of make personalized predictions. However, these systems are highly vulnerable to profile injection attacks. Group attacks are attacks that target a group of items instead of one, and there are common attributes among these items. Such profiles will have a good probability of being similar to a large number of user profiles, making them hard to detect. We propose a novel technique for identifying group attack profiles which uses an improved metric based on Degree of Similarity with Top Neighbors (DegSim) and Rating Deviation from Mean Agreement (RDMA). We also extend our work with a detailed analysis of target item rating patterns. Experiments show that the combined methods can improve detection rates in user-based recommender systems. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1145/2600428.2609483 | SIGIR |
Keywords | Field | DocType |
security,group attack,attack detection,recommender systems,information search and retrieval | Recommender system,Data mining,Degree of similarity,Injection attacks,Collaborative filtering,Information retrieval,Computer science,Remote direct memory access | Conference |
Citations | PageRank | References |
14 | 0.53 | 11 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wei Zhou | 1 | 14 | 2.55 |
| Yun Sing Koh | 2 | 393 | 39.52 |
| Junhao Wen | 3 | 150 | 33.25 |
| Shafiq Alam | 4 | 173 | 10.49 |
| Gill Dobbie | 5 | 728 | 77.75 |