상태 정보를 활용하여 악의적 사용자의 영향력을 최소화하는 추천 알고리즘
State Information Based Recommendation Algorithm for Minimizing the Malicious User’s Influence
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 인터넷의 성장과 함께 사용자들은 물건이나 화, 음악 등을 구매 할 때 여러 가지 추천 사이트를 참고한 다. 하지만 이러한 추천 사이트에는 악의으로 아이템의 평을 높이거나 낮추려는 악의인 사용자 (Sybil)들이 존재하며, 결과으로 추천시스템은 불완하거나 부정확한 결과를 일반 사용자들에게 추천할 수 있다. 본 논문에서 는 사용자 들이 생성하는 평들을 안정상태 (stable state) 불안정상태 (unstable state)로 구분하고, 상태 정보를 활용하여 악의 사용자의 향력을 최소화 하는 추천 알고리즘을 제안한다. 제안하는 기법의 성능을 입증하 기 해 유명한 화사이트에서 실제 데이터를 직 수집 (crawling)하여 성능분석을 진행하다. 성능분석결과 제 안하는 기법의 성능이 기존 알고리즘 보다 향상됨을 확인하다.
Abstract
With the extreme development of Internet, recently most users refer the sites with the various Recommendation Systems (RSs) when they want to buy some stuff, movie and music. However, the possibilities of the Sybils with the malicious behaviors may exists in these RSs sites in which Sybils intentionally increase or decrease the rating values. The RSs cannot play an accurate role of the proper recommendations to the general normal users. In this paper, we divide the given rating values into the stable or unstable states and propose a system information based recommendation algorithm that minimizes the malicious user’s influence. To evaluate the performance of the proposed scheme, we directly crawl the real trace data from the famous movie site and analyze the performance. After that, we showed proposed scheme performs well compared to existing algorithms.
참고문헌 (25)
- Adomavicius, G., "Toward the next generation of recommender systems : A survey of the state-of-the-art and possible extensions", Proceedings of the IEEE Transactions on Knowledge and Data Engineering, 17(6), pp.734~749 (2005)
- Ma, H., "Recommender systems with social regularization", Proceedings of the fourth ACM international conference on Web search and data mining, pp.287~296 (2014)
- Lang, K., "News weeder : Learning to filter net news", Proceeding of the Twelfth International Conference on Machine learning, pp.331~339 (1995)
- Linden, G., "Amazon. com recommendations : Item-to-item collaborative filtering", Proceedings of the IEEE Internet Computing, 7(1), pp.76~80 (2003)
- Melville, P., "Recommender systems", Proceedings of the Encyclopedia of machine learning, pp.829~838 (2010)
- Melville, P., "Content-boosted collaborative filtering for improved recommendations", Proceedings of the national conference on artificial intelligence, pp.187~192 (2002)
- "News of the small businesses"[URL]
- "MBC news about the inaccurate RSs"[URL]
- H. Yu, "Dsybil : Optimal Sybil-Resistance for Recommendation Systems", Proceedings of the 30th IEEE Symposium on Security and Privacy, pp.283~298 (2009)
- Z. Cheng, "Robust Collaborative Recommendation by Least Trimmed Squares Matrix Factorization", Proceedings of the 22nd IEEE International Conference on Tools with Artificial Intelligence, 2, pp.105~112 (2010)
- Y. Koren, "Matrix factorization techniques for recommender systems", Proceedings of IEEE Computer, 42(8), pp.30~37 (2009)
- Mehta, B., "Lies and propaganda: Detecting spam users in collaborative filtering", Proceedings of the 12th international conference on intelligent user interfaces, pp.14~21 (2007)
- B. Mobasher, "Toward Trustworthy Recommender Systems : An Analysis of Attack Models and Algorithm Robustness", Journal of ACM Transcations on Internet Technology, 7(4) (2007)
- N. Hurley, "Robustness of Recommender Systems", Proceedings of the fifth ACM conference on Recommender systems, pp.9~10 (2011)
- Mehta, B., "Attack resistant collaborative filtering", Proceedings of the 31st annual international ACM SIGIR conference on research and development in information retrieval, pp.75~82 (2008)
- J. Douceur, "The sybil attack", Proceedings of 1st International Workshop on Peer-to-Peer Systems, pp.251~260 (2002)
- B. Mobasher, "Modelbased collaborative filtering as a defense against profile injection attacks", Proceedings of the 21st National Conference on Artificial Intelligence and the 18th Innovative Applications of artificial Intelligence Conference, 2, pp.1388~1393 (2006)
- Gao Feng, "Robust Online Filter Recommended Algorithm based on Attack Profile", Proceedings of International Journal of Security and Its Applications, 8(4), pp.253~264 (2014)
- Giseop Noh, "Robust Sybil attack defense with information level in online Recommender Systems", Proceedings of the Expert Systems with Applications, 41(4), pp.1781~1791 (2014)
- Sheng Zhang, "Attack Detection in Time Series for Recommendation Systems", Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, pp.809~814 (2006)
- Man Li, "Shilling Attack Detection Algorithm based on Non-random-missing Mechanism", Proceedings of the International Journal of Security and Its Applications, 8(6), pp.115~126 (2013)
- Jie Cao, "Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system", Proceedings of the World Wide Web, 16(5), pp.729~748 (2013)
- Wei Zhou, "Attack detection in recommender systems based on target item analysis", Proceedings of the Neural Networks and International Joint Conference, pp.332~339 (2014)
- Zhuo Zhang, "Detection of Shilling Attacks in Recommender Systems via Spectral Clustering", Proceedings of the Information Fusion and 17th International Conference, pp.1~8 (2014)
- P. -A. Chirita, "Preventing shilling attacks in online recommender systems", Proceedings of the. 7th Annual ACM International Workshop on Web Information and Data Management, pp.67~74 (2005)