国防科技大学学报
國防科技大學學報
국방과기대학학보
JOURNAL OF NATIONAL UNIVERSITY OF DEFENSE TECHNOLOGY
2014年
2期
105-112
,共8页
常俊胜%庞征斌%徐炜遐%夏军%尹刚
常俊勝%龐徵斌%徐煒遐%夏軍%尹剛
상준성%방정빈%서위하%하군%윤강
信誉机制%推荐%信任%信誉
信譽機製%推薦%信任%信譽
신예궤제%추천%신임%신예
reputation mechanism%recommendation%trust%reputation
增强信誉机制对信誉信息的有效聚合能力是信誉系统成功的基础。已有的基于局部信誉信息的信誉系统难以有效处理节点的复杂策略不诚实推荐行为,并且可能把提供诚实推荐的节点错误划分为不诚实节点。对此,提出了一种可信度增强的信誉机制CERep。该机制中,节点基于自身的经验产生的直接信任评价,包含直接信任评价值和关于此评价值的信心因子两个部分。在此基础上,提出了新的基于信誉的信任评价算法和推荐可信度计算模型,并给出了信誉机制的分布式实现策略。分析和模拟实验表明,CERep信誉机制能够有效应对复杂策略的不诚实推荐行为,提高信任评价的准确性,实现对节点推荐可信度更公平的评价。
增彊信譽機製對信譽信息的有效聚閤能力是信譽繫統成功的基礎。已有的基于跼部信譽信息的信譽繫統難以有效處理節點的複雜策略不誠實推薦行為,併且可能把提供誠實推薦的節點錯誤劃分為不誠實節點。對此,提齣瞭一種可信度增彊的信譽機製CERep。該機製中,節點基于自身的經驗產生的直接信任評價,包含直接信任評價值和關于此評價值的信心因子兩箇部分。在此基礎上,提齣瞭新的基于信譽的信任評價算法和推薦可信度計算模型,併給齣瞭信譽機製的分佈式實現策略。分析和模擬實驗錶明,CERep信譽機製能夠有效應對複雜策略的不誠實推薦行為,提高信任評價的準確性,實現對節點推薦可信度更公平的評價。
증강신예궤제대신예신식적유효취합능력시신예계통성공적기출。이유적기우국부신예신식적신예계통난이유효처리절점적복잡책략불성실추천행위,병차가능파제공성실추천적절점착오화분위불성실절점。대차,제출료일충가신도증강적신예궤제CERep。해궤제중,절점기우자신적경험산생적직접신임평개,포함직접신임평개치화관우차평개치적신심인자량개부분。재차기출상,제출료신적기우신예적신임평개산법화추천가신도계산모형,병급출료신예궤제적분포식실현책략。분석화모의실험표명,CERep신예궤제능구유효응대복잡책략적불성실추천행위,제고신임평개적준학성,실현대절점추천가신도경공평적평개。
Enhancing reputation mechanism’s capability of aggregating reputation information effectively is the foundation of a successful reputation system.Current reputation systems based on localized reputation information cannot process such strategic recommendations as correlative and collusive ratings.Furthermore there exists unfairness to blameless peers in these models.Therefore,a Credibility Enhanced Reputation mechanism CERep is presented.In CERep,a peer uses its experiences to compute the direct trust valuation which contains direct trust value and level of confidence about this value,then a reputation-based trust valuation scheme and recommendation credibility computation model is proposed. Moreover,the strategies used for implementing the reputation mechanism are also discussed.Theoretical analysis and simulation show that CERep reputation mechanism proposed can help peers effectively detect dishonest recommendations in a variety of scenarios where more complex malicious strategies are introduced,and achieve a more accurate trust valuation and fair evaluation of recommendations.