Deep learning has been becoming a promising focus in data mining research. With deep learning techniques, researchers can discover deep properties and features of events from quantitative mobile sensor data. However, many data sources are geographically separated and have strict privacy, security, and regulatory constraints. Upon releasing the privacy-sensitive data, these data sources generally no longer physically possess their data and cannot interfere with the way their personal data being used. Therefore, it is necessary to explore distributed data mining architecture which is able to conduct consensus learning based on needs. Accordingly, we propose a distributed deep learning optimized system which contains a cloud server and multiple smartphone devices with computation capabilities and each device is served as a personal mobile data hub for enabling mobile computing while preserving data privacy. The proposed system keeps the private data locally in smartphones, shares trained parameters, and builds a global consensus model. The feasibility and usability of the proposed system are evaluated by three experiments and related discussion. The experimental results show that the proposed distributed deep learning system can reconstruct the behavior of centralized training. We also measure the cumulative network traffic in different scenarios and show that the partial parameter sharing strategy does not only preserve the performance of the trained model but also can reduce network traffic. User data privacy is protected on two levels. First, local private training data do not need to be shared with other people and the user has full control of their personal training data all the time. Second, only a small fraction of trained gradients of the local model are selected for sharing, which further reduces the risk of information leaking.

Anticensorship continues to be an arms race between citizens who use circumvention systems and the censors that find and block them. Many recently proposed circumvention systems have found ways to hide from deep-packet inspection (DPI), as well as active probing by the censors. However, many circumvention systems have trouble distributing the necessary resources to its users, and often use centralized distribution systems that can be easily blocked. In this paper, we design a censorship circumvention infrastructure called OverTorrent, that utilizes the BitTorrent protocol to allow peers to share their Internet connections with one another. As BitTorrent is a widely popular application, it remains largely uncensored even by technologically sophisticated censors such as China. Because OverTorrent is built on top of BitTorrent, it does not require any centralized infrastructure to operate. Peers are discovered while participating in the BitTorrent download of popular files that are unrelated to the OverTorrent protocol. Blocking OverTorrent requires blocking or actively interfering with certain types of popular BitTorrent clients. We believe this system could be used to disseminate other anticensorship tools or resources, or even allow access of websites directly.

Building models by mimicking the structures and functions of visual cortex has always been a major approach to implement a human-like intelligent visual system. Several feed-forward hierarchical models have been proposed and perform well on invariant feature extraction. However, less attention has been given to the biologically plausible feature matching model which mimics higher levels of the ventral stream. In this work, with the inspirations from both neuroscience and computer science, we propose a framework for rapid object recognition and present the feature-selective hashing scheme to model the memory association in inferior temporal cortex. The experimental results on 1000-class ALOI dataset demonstrate its efficiency and scalability of learning on feature matching. We also discuss the biological plausibility of our framework and present a bio-plausible network mapping of the feature-selective hashing scheme.