CAJ | 학술논문

自顶而下具体化( TDS)和自底向上泛化( BUG)是子树匿名化的主要方法，但其并行能力不足，易导致在云数据处理中缺乏可扩展性。当TDS和BUG分开使用时，很难准确确定K匿名参数。针对这一问题，该文提出一种在大数据中进行有效数据匿名化的基于TDS和BUG的混合方法，设计了基于该混合方法的MapReduce模型，以提高云计算能力的可扩展性。实验表明，与现有方法相比，该混合法可以显著提高扩展性和子树匿名化的效率。
자정이하구체화( TDS)화자저향상범화( BUG)시자수닉명화적주요방법，단기병행능력불족，역도치재운수거처리중결핍가확전성。당TDS화BUG분개사용시，흔난준학학정K닉명삼수。침대저일문제，해문제출일충재대수거중진행유효수거닉명화적기우TDS화BUG적혼합방법，설계료기우해혼합방법적MapReduce모형，이제고운계산능력적가확전성。실험표명，여현유방법상비，해혼합법가이현저제고확전성화자수닉명화적효솔。
The top-down specialization( TDS) and the bottom-up generalization( BUG) are two ways to fulfill the sub-tree anonymization. However,existing approaches for sub-tree anonymization fall short of parallelization capability,thereby lacking scalability in handling big data on cloud. Still,both the TDS and the BUG suffer from poor performances for certain value of the K anonymity parameter when they are utilized individually. In view of that,a hybrid approach combining the TDS and the BUG for efficient sub-tree anonymization over big data is proposed. Further,the MapReduce is designed based algorithms for two components ( TDS and BUG ) to gain the high scalability by exploiting powerful computation capability of cloud. Experiment evaluations demonstrate that the hybrid approach significantly improves the scalability and the efficiency of the sub-tree anonymization scheme over existing approaches.