| 摘要: | 現今由於雲端服務越來越普及，不僅僅是雲端服務供應商，其他產業的業者也開始蒐集使用者的資訊上傳至雲端進行儲存和分析，以期提供更好的使用者體驗服務，但蒐集大量資料的同時，要如何去保障使用者的隱私是一個相當重要的議題。
有研究提出以匿名方式進行使用者資訊保護，基於布隆過濾器來保障雲端環境下的使用者資訊，並且在匿名的同時還能夠提供查詢服務。但此機制有資料容納數量上的限制，且當資料負載量提高時，插入和搜尋資料的時間成本也會跟著提高，造成效能下降。
因此所以本研究提出Decay-Cuckoo Filter，在布穀鳥過濾器的雜湊表上做了一些改良，在原有的Bucket之後加上第二組Associate Bucket，用來儲存衰減係數(Decay Value)，一開始插入元素時，該元素的衰減係數為最大值，而此係數會隨著時間的經過、插入元素數量或者查詢元素素量達設定值後執行「衰減」，當某元素衰減係數衰減至最小值“0”，該元素將從資料表中被刪除，釋放空間。且本研究實驗證明，使用Decay Function方法其元素插入時間效能提升了1.4倍，元素的查詢時間效能提升了2倍。;Nowadays, due to the increasing popularity of cloud services, not only cloud service providers, but also industry players in other industries have begun to collect user information and upload it to the cloud for storage and analysis, in order to provide better user experience services, but collect a large amount of data. At the same time, how to protect the privacy of users is a very important issue.
Some studies have proposed to protect user information in an anonymous manner. Based on the Bloom filter, user information in the cloud environment is guaranteed, and the query service can be provided while being anonymous. However, this mechanism has a limitation on the number of data storage, and as the data load increases, the time cost of inserting and searching for data will also increase, resulting in a decrease in performance.
Therefore, this study proposes a Decay Value as the usage weight value of each data, and a set of Decay Function to let the attenuation value decay with the custom conditions, when the attenuation value is reduced to At the minimum value, the data is removed from the data sheet to release the location, extending the life of the data sheet and improving its performance. And this research experiment proves that using the Decay Function method, the element insertion time is increased by 1.4 times, and the element query time is increased by 2 times. |
