Personalized Federated Learning (PFL) enhances traditional Federated Learning (FL) by addressing the challenges associated with non-independent and identically distributed (non-IID) data and retains FL’s privacy-preserving feature. However, this decentralized architecture still presents security challenges. This study focuses on data poisoning attacks, particularly label flipping attacks in PFL, where some malicious clients upload poisoned model parameters to the server, which could then compromise the personalized models of honest clients during the server’s aggregation process. Moreover, we discovered that even with a small number of attackers, targeted data poisoning attacks are feasible and can significantly affect the model’s performance on specific labels. Finally, we propose four defensive strategies that have proven effective in identifying malicious clients. Additionally, we provide a framework that assists users in selecting the most suitable defense strategy based on their specific circumstances, thereby enhancing the robustness of the PFL architecture.

Time-killing on smartphones has become a pervasive activity, and could be opportune for delivering content to their users. This research is believed to be the first attempt at time-killing detection, which leverages the fusion of phone-sensor and screenshot data. We collected nearly one million user-annotated screenshots from 36 Android users. Using this dataset, we built a deep-learning fusion model, which achieved a precision of 0.83 and an AUROC of 0.72. We further employed a two-stage clustering approach to separate users into four groups according to the patterns of their phone-usage behaviors, and then built a fusion model for each group. The performance of the four models, though diverse, yielded better average precision of 0.87 and AUROC of 0.76, and was superior to that of the general/unified model shared among all users. We investigated and discussed the features of the four time-killing behavior clusters that explain why the models’ performance differ.

Using a mixed-methods approach over six weeks, we studied 30 smartphone users’ task choices, task execution and effort devoted to two commercial mobile crowdsourcing platforms in the wild. We focused on the influence of activity contexts, characterized by breakpoint situations and activity attributes. In line with their stated preferences, the participants were more likely to proactively perform mobile crowdsourcing tasks during transitions between activities than during an ongoing activity and during long breaks, respectively. Their task choices were influenced by various activity attributes, and more impacted by their current and preceding activities than their upcoming ones. Two of our three target outcomes, task execution and task choice, were also influenced by individuals’ stress and energy levels. Our qualitative data provide further insights into participants’ decisions about which crowdsourcing tasks to perform and when; and our results’ implications for the design of future mobile crowdsourcing task-prompting mechanisms are also discussed.

This paper introduces Glissade, a digital pen that generates balance shifting feedback by changing the weight distribution of the pen. A pulley system shifts a brass mass inside the pen to change the pen's center of mass and moment of inertia. When the mass is stationary, the pen delivers a constant yet natural sensation of weight, which can be used to convey a status. The pen can also generate a variety of haptic clues by actuating the mass according to the tilt or rotation of the pen, two commonly-used auxiliary pen input channels. Glissade demonstrates new possibilities that balance shifting feedback can bring to digital pen interactions. We validated the usability of this feedback by determining the recognizability of six balance patterns – a mix of static and dynamic patterns chosen based on our design considerations – in two controlled experiments. The results show that, on average, the participants could distinguish between the patterns with a 94.25% accuracy. At the end, we demonstrate a set of novel interactions enabled by Glissade and discuss the directions for future research.

The human ear is highly sensitive and accessible, making it especially suitable for being used as an interface for interacting with smart earpieces or augmented glasses. However, previous works on ear-based input mainly address gesture sensing technology and researcher-designed gestures. This paper aims to bring more understandings of gesture design. Thus, for a user elicitation study, we recruited 28 participants, each of whom designed gestures for 31 smart device-related tasks. This resulted in a total of 868 gestures generated. Upon the basis of these gestures, we compiled a taxonomy and concluded the considerations underlying the participants' designs that also offer insights into their design rationales and preferences. Thereafter, based on these study results, we propose a set of user-defined gestures and share interesting findings. We hope this work can shed some light on not only sensing technologies of ear-based input, but also the interface design of future wearable interfaces.

With the recent emergence of naked-eye 3D mobile devices and various 3D-enabled laptops, service providers now afford the opportunity to provide mobile 3D video streaming in LTE-Advanced networks. Differing from traditional single-view 3D videos, multi-view 3D videos allow users to choose preferred view angles and thus are promising for new applications, such as free-viewpoint television (FTV). Nevertheless, enabling multi-view 3D video services may overwhelm the network resource when transmitting all views of every video. Fortunately, Depth-Image-Based Rendering (DIBR) allows each mobile client to synthesize the desired view from a nearby left view and right view, so that not all views of a video are necessarily transmitted. A new challenge with DIBR, however, is to carefully choose the transmitted views to limit the video distortion and minimize the bandwidth consumption. In this paper, therefore, we first formulate a new optimization problem, called View and MCS Selection (VMS) Problem, to minimize the bandwidth consumption for multi-view 3D video multicast in LTE networks. An algorithm, called View and MCS Aggregation (VMAG) is proposed to find the optimal solution to VMS. For Carrier Aggregation (CA) in LTE-Advanced networks, we formulate a new View, MCS and Carrier Selection (VMCS) Problem and prove that the problem is NP-Hard. We first design a dynamic programming algorithm, called the View Assignment with MCS and Carrier (VAMC) algorithm, to find the optimal solution for small instances. We then propose the View and MCS Aggregation with Carrier (VMAGC) algorithm based on VMAG to effectively find the near-optimal solution to VMCS. The simulation results show that bandwidth consumption can be effectively reduced by over 30 percent in VMS and VMCS.

Vehicle detection is an important research problem for Advanced Driver Assistance Systems to improve driving safety. Most existing methods are based on the sliding window search framework to locate vehicles in an image. However, such methods usually produce large numbers of false positives and are computationally intensive. In this paper, we propose an efficient vehicle detection algorithm that dramatically reduces the search space based on the perspective geometry of the road. In the training phase, we search a few images to locate all possible vehicle regions by using the standard HOG-based vehicle detector. Pairs of vehicle candidates that satisfy the projective geometry constraints are used to estimate the linear vehicle width model with respect to y coordinates in the image. Then an adaptive scan strategy based on the estimated vehicle width model is proposed to efficiently detect vehicles in an image. Experimental results show that the proposed algorithm provides improved performance in terms of both speed and accuracy compared to standard sliding-windows search strategy.

Generally, header compression can be used with packet aggregation to make more efficient use of wireless bandwidth. Header compression reduces the waste of the header size, while packet aggregation reduces the number of packets. Unfortunately, packet aggregation might increase the end-to-end delay in multi-hop vehicular environment. The goal of this paper focuses on header compression and packet aggregation in vehicular networks. We propose an adaptive packet aggregation mechanism for header compression. The proposed mechanism will make a tradeoff between delay time and compression efficiency. Finally, we used the ns-2 simulator to perform the simulation experiments. Simulation results showed that our proposed mechanism performs better than the existing schemes which did not aggregate packets adaptively for data transmission in terms of the average end to end delay and packet arrival rate.