PPaaS: Privacy Preservation as a Service

Personally identifiable information (PII) can find its way into cyberspace through various channels, and many potential sources leak such information. Data sharing (e.g. cross-agency data sharing) for machine learning analytics is one of the important components in science. However, due to privacy concerns, should be enforced with strong guarantees before sharing. Different privacy-preserving approaches were developed preserving sharing; however, identifying best privacy-preservation approach a certain dataset still challenge. parameters influence efficacy process, as characteristics input dataset, strength approach, expected level utility resulting (on corresponding mining application classification). This paper presents framework named \underline{P}rivacy \underline{P}reservation \underline{a}s \underline{a} \underline{S}ervice (PPaaS) reduce this complexity. The proposed method employs selective preservation via perturbation looks at different dynamics that quality dataset. PPaaS includes pools methods, each selects most suitable after rigorous evaluation. It enhances usability methods within pool; it generic platform used sanitize big granular, application-specific manner by employing combination diverse algorithms provide proper balance between utility.