Limits...
Shilling Attacks Detection in Recommender Systems Based on Target Item Analysis.

Zhou W, Wen J, Koh YS, Xiong Q, Gao M, Dobbie G, Alam S - PLoS ONE (2015)

Bottom Line: Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach.In order to detect more complicated attack models, we propose a novel metric called DegSim' based on DegSim.The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science, Chongqing University, Chongqing, China.

ABSTRACT
Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Attackers who introduce biased ratings in order to affect recommendations, have been shown to negatively affect collaborative filtering (CF) algorithms. Previous research focuses only on the differences between genuine profiles and attack profiles, ignoring the group characteristics in attack profiles. In this paper, we study the use of statistical metrics to detect rating patterns of attackers and group characteristics in attack profiles. Another question is that most existing detecting methods are model specific. Two metrics, Rating Deviation from Mean Agreement (RDMA) and Degree of Similarity with Top Neighbors (DegSim), are used for analyzing rating patterns between malicious profiles and genuine profiles in attack models. Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach. In order to detect more complicated attack models, we propose a novel metric called DegSim' based on DegSim. The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks.

No MeSH data available.


Detection rate of single-targeted attacks when attack size and filler size varies.There is only one target item in each attack. Comparison of detection rate when attack size and filler size varies.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4519300&req=5

pone.0130968.g009: Detection rate of single-targeted attacks when attack size and filler size varies.There is only one target item in each attack. Comparison of detection rate when attack size and filler size varies.

Mentions: In the second test, we compare our method with the state-of-the-art unsupervised βρ-based method in [31] using ML100k Dataset when the selected set is none, that is, there is only one target item in an attack profile, and the filler size is 5% and the attack size varies from 1%, 3%, 5%, 7% to 9%. Fig 9 shows the detection rates of βρ-based method (A) and our method (B) when facing single-targeted push attacks. In our method (B), the detection rate reaches almost 100% when the filler size is greater than 4%. The false positive rates are lower.


Shilling Attacks Detection in Recommender Systems Based on Target Item Analysis.

Zhou W, Wen J, Koh YS, Xiong Q, Gao M, Dobbie G, Alam S - PLoS ONE (2015)

Detection rate of single-targeted attacks when attack size and filler size varies.There is only one target item in each attack. Comparison of detection rate when attack size and filler size varies.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4519300&req=5

pone.0130968.g009: Detection rate of single-targeted attacks when attack size and filler size varies.There is only one target item in each attack. Comparison of detection rate when attack size and filler size varies.
Mentions: In the second test, we compare our method with the state-of-the-art unsupervised βρ-based method in [31] using ML100k Dataset when the selected set is none, that is, there is only one target item in an attack profile, and the filler size is 5% and the attack size varies from 1%, 3%, 5%, 7% to 9%. Fig 9 shows the detection rates of βρ-based method (A) and our method (B) when facing single-targeted push attacks. In our method (B), the detection rate reaches almost 100% when the filler size is greater than 4%. The false positive rates are lower.

Bottom Line: Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach.In order to detect more complicated attack models, we propose a novel metric called DegSim' based on DegSim.The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science, Chongqing University, Chongqing, China.

ABSTRACT
Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Attackers who introduce biased ratings in order to affect recommendations, have been shown to negatively affect collaborative filtering (CF) algorithms. Previous research focuses only on the differences between genuine profiles and attack profiles, ignoring the group characteristics in attack profiles. In this paper, we study the use of statistical metrics to detect rating patterns of attackers and group characteristics in attack profiles. Another question is that most existing detecting methods are model specific. Two metrics, Rating Deviation from Mean Agreement (RDMA) and Degree of Similarity with Top Neighbors (DegSim), are used for analyzing rating patterns between malicious profiles and genuine profiles in attack models. Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach. In order to detect more complicated attack models, we propose a novel metric called DegSim' based on DegSim. The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks.

No MeSH data available.