Activity-Free User Identification Using Wearables Based on Vision Techniques.

In order to achieve the promise of smart spaces where the environment acts to fulfill the needs of users in an unobtrusive and personalized manner, it is necessary to provide means for a seamless and continuous identification of users to know who indeed is interacting with the system and to whom the smart services are to be provided. In this paper, we propose a new approach capable of performing activity-free identification of users based on hand and arm motion patterns obtained from an wrist-worn inertial measurement unit (IMU). Our approach is not constrained to particular types of movements, gestures, or activities, thus, allowing users to perform freely and unconstrained their daily routine while the user identification takes place. We evaluate our approach based on IMU data collected from 23 people performing their daily routines unconstrained. Our results indicate that our approach is able to perform activity-free user identification with an accuracy of 0.9485 for 23 users without requiring any direct input or specific action from users. Furthermore, our evaluation provides evidence regarding the robustness of our approach in various different configurations.

Improving Wearable-Based Activity Recognition Using Image Representations.

Activity recognition based on inertial sensors is an essential task in mobile and ubiquitous computing. To date, the best performing approaches in this task are based on deep learning models. Although the performance of the approaches has been increasingly improving, a number of issues still remain. Specifically, in this paper we focus on the issue of the dependence of today's state-of-the-art approaches to complex ad hoc deep learning convolutional neural networks (CNNs), recurrent neural networks (RNNs), or a combination of both, which require specialized knowledge and considerable effort for their construction and optimal tuning. To address this issue, in this paper we propose an approach that automatically transforms the inertial sensors time-series data into images that represent in pixel form patterns found over time, allowing even a simple CNN to outperform complex ad hoc deep learning models that combine RNNs and CNNs for activity recognition. We conducted an extensive evaluation considering seven benchmark datasets that are among the most relevant in activity recognition. Our results demonstrate that our approach is able to outperform the state of the art in all cases, based on image representations that are generated through a process that is easy to implement, modify, and extend further, without the need of developing complex deep learning models.

Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setups.

Deep learning pervades heavy data-driven disciplines in research and development. The Internet of Things and sensor systems, which enable smart environments and services, are settings where deep learning can provide invaluable utility. However, the data in these systems are very often directly or indirectly related to people, which raises privacy concerns. Federated learning (FL) mitigates some of these concerns and empowers deep learning in sensor-driven environments by enabling multiple entities to collaboratively train a machine learning model without sharing their data. Nevertheless, a number of works in the literature propose attacks that can manipulate the model and disclose information about the training data in FL. As a result, there has been a growing belief that FL is highly vulnerable to severe attacks. Although these attacks do indeed highlight security and privacy risks in FL, some of them may not be as effective in production deployment because they are feasible only given special-sometimes impractical-assumptions. In this paper, we investigate this issue by conducting a quantitative analysis of the attacks against FL and their evaluation settings in 48 papers. This analysis is the first of its kind to reveal several research gaps with regard to the types and architectures of target models. Additionally, the quantitative analysis allows us to highlight unrealistic assumptions in some attacks related to the hyper-parameters of the model and data distribution. Furthermore, we identify fallacies in the evaluation of attacks which raise questions about the generalizability of the conclusions. As a remedy, we propose a set of recommendations to promote adequate evaluations.