We consider a private distributed online optimization problem (PDOOP) where a set of agents aim to minimize the sum of locally convex cost functions while each desires that the locally cost function of individual agents is kept differentially private. To solve such problem, we propose differentially private distributed stochastic subgradient online optimization algorithm over time-varying directed networks. We use differential privacy to preserve the privacy of individual agents. We show that our algorithm can achieve differential privacy and achieves logarithmic expected regret under local strong convexity. Moreover, we also show that square-root expected regret can be obtained under local convexity. Furthermore, we reveal the trade-off between the privacy level and the performance of our algorithm.

With the rise of Internet of Things (IoT), the number of mobile devices with sensing and computing capabilities increases dramatically, paving the way towards an emerging paradigm, i.e., crowdsensing which facilitates the interactions between humans and the surrounding physical world. Despite its superiority, particular attention is paid to be able to submit sensing data to the platform wherever possible to avoid leaking the sensitive information of participants, and to incentivize them to improve sensing quality. In this paper, we propose an incentive mechanism for participants, aiming to protect them from privacy leakage, ensure the availability of sensing data and maximize the utilities of both platforms and participants by means of distributing different sensing tasks to different participants. More specifically, we formulate the interactions between platforms and participants as a multi-leader multi-follower Stackelberg game and derive the Stackelberg equilibrium (SE) of the game. Due to the difficulty to obtain the optimal strategy, a reinforcement learning algorithm, i.e., Q-learning is adopted to obtain the optimal sensing contributions of participants. In order to accelerate learning speed and reduce overestimation, a deep learning algorithm combined with Q-learning in a dueling network architecture, i.e., double deep Q network with dueling architecture (DDDQN) is proposed to obtain the optimal payment strategies of platforms. To evaluate the performance of our proposed mechanism, extensive simulations are conducted to show the superiority of our proposed mechanism compared with state-of-the-art approaches.

The Internet of Things (IoT) has such a profound impact that we have witnessed crowdsensing has emerged as the most popular sensing paradigm where participants sense and aggregate data to the platform by smart devices. However, the participants may not be willing to involve in data sensing and aggregation if they are not sufficiently compensated or their personalized private information are disclosed. In order to overcome the above issues, this paper proposes a payment-privacy protection level (PPL) game, where each participant submits his sensing data with a specified PPL while the platform chooses a corresponding payment to the participant. Additionally, we derive the Nash equilibrium (NE) point of the game. Considering that the payment-PPL model is unknown in practice, we employ a reinforcement learning technique, i.e., Q-learning to obtain the payment-PPL strategy in a dynamic payment-PPL game. We further use deep Q network (DQN), which combines a deep learning technique with Q-learning to accelerate learning speed. Through extensive simulations, we verify that our proposed algorithm using DQN achieves superior performance in terms of utilities of both platform and participants and data aggregation accuracy compared with the one using Q-learning.

With the development of various deep learning algorithms, the importance and potential of AI + medical treatment are increasingly prominent. Electrocardiogram (ECG) as a common auxiliary diagnostic index of heart diseases, has been widely applied in the pre-screening and physical examination of heart diseases due to its low price and non-invasive characteristics. Currently, the multi-lead ECG equipments have been used in the clinic, and some of them have the automatic analysis and diagnosis functions. However, the automatic analysis is not accurate enough for the discrimination of abnormal events of ECG, which needs to be further checked by doctors. We therefore develop a deep-learning-based approach for multi-label classification of ECG named Multi-ECGNet, which can effectively identify patients with multiple heart diseases at the same time. The experimental results show that the performance of our methods can get a high score of 0.863 (micro-F1-score) in classifying 55 kinds of arrythmias, which is beyond the level of ordinary human experts.

Space-air-ground integrated networks (SAGINs) allow mobile nodes to gain access to the Internet anywhere and at any time, which has significantly broadened the communication coverage all over the world. Different from other heterogeneous networks, SAGINs have the characteristics of dynamic network and wide coverage, which make it vulnerable to various malicious attacks. To improve the security of SAGINs, researchers are facing many sophisticated challenges, in which access authentication is the primary problem to be solved because is mainly used to prevent illegal nodes from accessing SAGINs for network services. Therefore, it is crucial to design a secure and lightweight access authentication scheme for SAGINs. In this article, we propose an identity-based mutual authentication scheme (IMAS), which consists of three segments and five procedural phases. Multicast communication is first introduced in access authentication for re-authentication message transmission, which can greatly reduce authentication delay and signaling overhead during handover. Our further qualitative analysis shows that IMAS has proper security characteristics which can meet various security requirements. In addition, from the perspective of performance evaluation, IMAS has outperformed the existing schemes especially when mobile nodes change their access points frequently and need to be re-authenticated for accessing requests.