模糊聚类算法在数据库水印中的应用  

Application of Fuzzy Clustering Algorithm in Database Watermarking

作　　者：狄冠东 程润辉 咸鹤群 DI Guan-dong;CHENG Run-hui;XIAN He-qun(College of Computer Science & Technology, Qingdao University, Qingdao 266071, China;Xinhua News Agency Mobile TV Station, Beijing 100053, China)

机构地区：[1]青岛大学计算机科学技术学院,青岛266071 [2]新华社手机电视台,北京100053

出　　处：《青岛大学学报（自然科学版）》2020年第4期20-23,30,共5页Journal of Qingdao University(Natural Science Edition)

基　　金：山东省自然科学基金(批准号:ZR2019MF058)资助。

摘　　要：当前数据库水印技术存在版权证明次数受限与无法抗密钥泄露的问题,一旦参数泄露,水印信息将被完全暴露。为此,提出一种基于FCM模糊聚类的水印方案,利用聚类算法筛选嵌入水印的元组,并通过分类器来完成水印的检测和数据的恢复。研究结果表明,该方案可多次证明版权,即使密钥及水印参数暴露依然不会暴露水印信息,对常见的数据攻击表现出较好的鲁棒性,具有一定商业价值。The current database watermarking technology has the problems of limited number of copyright certifications and inability to resist key leakage.Once the parameters are leaked,the watermark information will be completely exposed.Aiming at the above problems,a watermarking scheme based on FCM fuzzy clustering is proposed.The tuples embedded in the watermark are filtered through the clustering algorithm,and the watermark detection and data recovery are completed through the classifier.The research results show that this scheme can prove copyright multiple times,even if the key and watermark parameters are exposed,the watermark information will not be exposed,and it can show good robustness against common data attacks and has certain commercial value.

关 键 词：数据库水印 版权 聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]