We consider medical image transformation problems where a grayscale image is transformed into a color image. The colorized medical image should have the same features as the input image because extra synthesized features can increase the possibility of diagnostic errors. In this paper, to secure colorized medical images and improve the quality of synthesized images, as well as to leverage unpaired training image data, a colorization network is proposed based on the cycle generative adversarial network (CycleGAN) model, combining a perceptual loss function and a total variation (TV) loss function. Visual comparisons and experimental indicators from the NRMSE, PSNR, and SSIM metrics are used to evaluate the performance of the proposed method. The experimental results show that GAN-based style conversion can be applied to colorization of medical images. As well, the introduction of perceptual loss and TV loss can improve the quality of images produced as a result of colorization better than the result generated by only using the CycleGAN model.

E-wallets have started to grow in popularity, reaching a tipping point in some countries. This can be attributed to the worldwide use of payment-enabled devices and ubiquity of e-wallet acceptance by larger and smaller retailers. As more customers adopt e-wallets they may also become a big target of cybercrime. E-wallets facilitates financial transactions via smartphones which is a lucrative opportunity for cybercriminals. This paper presents a security assessment of the Android e-wallet apps provided by the Canada's leading banks.

Crowdsensing applications provide platforms for sharing sensing data collected by mobile devices. A blockchain system has the potential to replace a traditional centralized trusted third party for crowdsensing services to perform operations that involve evaluating the quality of sensing data, finishing payment, and storing sensing data and so forth. The requirements which are codified as smart contracts are executed to evaluate the quality of sensing data in a blockchain. However, regardless of the fact that the quality of sensing data may actually be sufficient, one key challenge is that malicious requesters can deliberately publish abnormal requirements that cause failure to occur in the quality evaluation process. If requesters control a miner node or full node, they can access the data without making payment; this is because of the transparency of data stored in the blockchain. This issue promotes unfair dealing and severely lowers the motivation of workers to participate in crowdsensing tasks. We (i) propose a novel crowdsensing scheme to address this issue using Trusted Execution Environments; (ii) offer a solution for the confidentiality and integrity of sensing data, which is only accessible by the worker and corresponding requester; (iii) and finally, report on the implementation of a prototype and evaluate its performance. Our results demonstrate that the proposed solution can guarantee fairness without a significant increase in overhead.

Truth discovery is an effective technique for resolving data conflicts in crowdsensing. Fog-based mobile crowdsensing utilizes low-latency and high-efficiency communications capabilities of fog computing to achieve large-scale data sensing at a low cost. Privacy-preserving truth discovery (PPTD) has garnered significant attention in recent years due to the inclusion of users' sensitive information in sensory data. However, existing PPTDs have not adequately addressed fog servers' reliability and mobile devices' efficiency simultaneously. Challenges are that fog servers are susceptible to breakdowns and collusion that causes privacy breaches, while mobile devices have limited resources. We thus propose a reliable and efficient PPTD for fog-based crowdsensing. We employ a threshold secret sharing scheme to establish secure multi-party computation primitives. These primitives are then used to construct an arithmetic circuit-an essential component of the PPTD. This approach preserves privacy of sensory data, as well as intermediate and final results, while accounting for server collusion, dropout, and mobile devices' efficiency. It has $T$ -out-of- $N$ threshold reliability that resists ( $T-1$ ) servers' collusion and ( $N-T$ ) servers' dropout. Experimental results demonstrate that our scheme reduces worker processing time by at least one order of magnitude and network communication overhead by approximately two orders of magnitude compared to existing PPTD methods.

Overconfidence in deep neural networks (DNN) reduces the model’s generalization performance and increases its risk. The deep ensemble method improves model robustness and generalization of the model by combining prediction results from multiple DNNs. However, training multiple DNNs for model averaging is a time-consuming and resource-intensive process. Moreover, combining multiple base learners (also called inducers) is hard to master, and any wrong choice may result in lower prediction accuracy than from a single inducer. We propose an approximation method for deep ensembles that can obtain ensembles of multiple DNNs without any additional costs. Specifically, multiple local optimal parameters generated during the training phase are sampled and saved by using an intelligent strategy. We use cycle learning rates starting at 75% of the training process and save the weights associated with the minimum learning rate in every iteration. Saved sets of the multiple model parameters are used as weights for a new model to perform forward propagation during the testing phase. Experiments on benchmarks of two different modalities, static images and dynamic videos, show that our method not only reduces the calibration error of the model but also improves the accuracy of the model.