Set-Based Adaptive Distributed Differential Evolution for Anonymity-Driven Database Fragmentation

Abstract By breaking sensitive associations between attributes, database fragmentation can protect the privacy of outsourced data storage. Database algorithms need prior knowledge in tackled and set it as optimization objective. Thus, effectiveness these is limited by knowledge. Inspired anonymity degree measurement techniques such k -anonymity, an anonymity-driven problem defined this paper. For problem, a set-based adaptive distributed differential evolution (S-ADDE) algorithm proposed. S-ADDE adopts island model to maintain population diversity. Two operators, i.e., mutation crossover, are designed which continuous domain traditional transferred discrete problem. Moreover, operator, each individual’s strategy adaptively selected according performance. The experimental results demonstrate that proposed significantly better than compared approaches. operators verified.