CAJ | 학술논문

在网格环境中,推荐系统通过提供高品质的个性化推荐,帮助网格用户选择更好的服务.另外,推荐系统也应用于虚拟机管理平台来评估虚拟机的性能和可靠性.然而,推荐结果对用户偏好信息的敏感性使得推荐系统易受到人为攻击(用户概貌注入攻击或托攻击).本文中,我们提出并评估了一种新的基于信任的安全检测算法以保护推荐系统抵御用户概貌注入攻击.并且,我们分别在用户级和项目级上讨论了信任检测与RDMA检测的结合.最后,我们通过试验表明这些新的安全检测机制可以取得更好的检测精度.
재망격배경중,추천계통통과제공고품질적개성화추천,방조망격용호선택경호적복무.령외,추천계통야응용우허의궤관리평태래평고허의궤적성능화가고성.연이,추천결과대용호편호신식적민감성사득추천계통역수도인위공격(용호개모주입공격혹탁공격).본문중,아문제출병평고료일충신적기우신임적안전검측산법이보호추천계통저어용호개모주입공격.병차,아문분별재용호급화항목급상토론료신임검측여RDMA검측적결합.최후,아문통과시험표명저사신적안전검측궤제가이취득경호적검측정도.
Recommender systems could be applied in grid environment to help grid users select more suitable services by making high quality personalized recommendations. Also, recommendation could be employed in the virtual machines managing platform to measure the performance and creditability of each virtual machine. However, such systems have been shown to be vulnerable to pro-file injection attacks (shilling attacks), attacks that involve the insertion of malicious profiles into the ratings database for the purpose of altering the system's recommendation behavior. In this paper we introduce and evaluate a new trust-based detecting algorithm for protecting recommender systems against profile injection attacks. Moreover, we discuss the combination of our trust-based metrics with previous metrics such as RDMA in profile-level and item-level respectively. In the end, we show these metrics can lead to improved detecting accuracy experimentally.