In today's Internet, recommender systems play an indispensable role in helping users discover items of interests, such as products, books, movies and so on. However, a higher recommendation accuracy is commonly at the cost of more disclosure of user privacy. Thus, a wider adoption of recommender systems poses significant security and privacy concerns to users. In this article, we propose a light-weight privacy-preserving framework calledRAPfor recommender systems, which can protect user privacy while still ensuring a high recommendation accuracy. Instead of directly sending users’ private ratings to the recommender, users first conduct a local perturbation operation on private ratings, and then send the perturbed ratings to the recommender. The recommender can run recommendation algorithms directly over the perturbed ratings and return the results to users. Different from crypto-based methods, our perturbation and de-perturbation methods are linear operations. Thus,RAPis light-weight and highly efficient in privacy protection. To be more rigorous, we formally prove that the order of recommendation accuracy will not decrease when ourRAPframework is applied to any MF (Matrix Factorization)-based recommender systems. We also derive the closed-form expression for the degree of privacy preservation of our framework. Finally, we conduct extensive evaluations using large-scale real-world datasets to verify the effectiveness of ourRAPframework and compare with other baseline algorithms. The results show that ourRAPframework can improve the degree of privacy preservation from zero to over 0.5 for theMovielensdataset and 4 for theJesterdataset, and still maintain the approaching level of recommendation accuracy.

Variable Bitrate (VBR) video encoding can provide much high quality-to-bits ratio compared to the widely adopted Constant Bitrate (CBR) encoding, and thus receives significant attentions by content providers in recent years. However, it is challenging to design efficient adaptive bitrate algorithms for VBR-encoded videos due to the sharply fluctuating chunk size and the resulting bitrate burstiness. In this paper, we propose a neural adaptive streaming framework called Vibra for VBR-encoded videos, which can well accommodate the high fluctuation of video chunk sizes and improve the quality-of-experience (QoE) of end users significantly. Our framework takes the characteristics of VBR-encoded videos into account, and adopts the technique of deep reinforcement learning to train a model for bitrate adaptation. We also conduct extensive trace-driven experiments, and the results show that Vibra outperforms the state-of-the-art ABR algorithms with an improvement of 8.17% -- 29.21% in terms of the average QoE.

Driven by the vision of the Internet of Things (IoT) under the fifth-generation (5G) wireless network, computing resource trading attracts numerous attention from both academia and industry. Prior works mainly focus on the design of auction mechanisms to implement pricing and resource allocation. However, it is still a challenging problem because of the following three aspects: 1) How to ensure that the auction mechanism runs fairly? An auction mechanism is vulnerable and questionable since the auctioneer may fail the orders matching operation or collude with a few peers. 2) It's hard to assign the computing resources of providers to customers and guarantee reasonable rewards for each participator. 3) How to make bidding strategies for each participator? Each participator has its willingness to selWuy, which are time-variant and private. To address the above issues, we build a blockchain-enabled computing resource trading system that takes both pricing and bidding strategies into consideration, on which providers and customers can trade computing resources securely, safely and willingly. Next, we formulate a decision-making problem in the continuous double auction (CDA) to maximize their payoffs. Then, we propose a universal model-free Deep Reinforcement Learning (DRL) framework for both computing resource providers and customers. We conduct extensive experiments to evaluate the performance of our DRL framework. Simulation results show that our solution outperforms others in both static and dynamic scenarios. Our DRL framework can achieve higher rewards than others by at least 35%. Furthermore, the average trading price from our DRL framework is less volatile than that from the compared methods. The DRL framework promotes trading and brings larger trading quantities, thus resulting in higher social welfare by at least 25% than the compared schemes.