With the continuous promotion and deepened application of Machine Learning-as-a-Service
(MLaaS) across various societal domains, its privacy problems occur frequently and receive …

From the previous chapter, we have learned that federated learning (FL) can be used to
protect data privacy since users no longer share their raw data during collaborative training …

The fields of artificial intelligence (AI) and machine learning (ML) have been popular tools
for data analysis at the edge, particularly through complex deep and convolutional neural …

Obtaining well-performed deep neural networks usually requires expensive data collection
and training procedures. Accordingly, they are valuable intellectual properties of their …

Due to the low adaptability to the characteristics of the database of vocational colleges, it is
difficult to guarantee the effectiveness of the intelligent query results of the database …

Recent years have witnessed the rapid development of deep learning in many domains.
These successes inspire using deep learning in the area of security. However, there are at …