Federated Learning (FL) enables collaborative model training across distributed devices while safeguarding data and user privacy. However, FL remains susceptible to privacy threats that can compromise data via direct means. That said, indirectly compromising the confidentiality of the FL model architecture (e.g., a convolutional neural network (CNN) or a recurrent neural network (RNN)) on a client device by an outsider remains unexplored. If leaked, this information can enable next-level attacks tailored to the architecture. This paper proposes a novel side-channel fingerprinting attack, leveraging flow-level and packet-level statistics of encrypted wireless traffic from an FL client to infer its deep learning model architecture. We name it FLARE, a fingerprinting framework based on FL Architecture REconnaissance. Evaluation across various CNN and RNN variants-including pre-trained and custom models trained over IEEE 802.11 Wi-Fi-shows that FLARE achieves over 98% F1-score in closed-world and up to 91% in open-world scenarios. These results reveal that CNN and RNN models leak distinguishable traffic patterns, enabling architecture fingerprinting even under realistic FL settings with hardware, software, and data heterogeneity. To our knowledge, this is the first work to fingerprint FL model architectures by sniffing encrypted wireless traffic, exposing a critical side-channel vulnerability in current FL systems.

Navigating large-scale outdoor environments requires complex reasoning in terms of geometric structures, environmental semantics, and terrain characteristics, which are typically captured by onboard sensors such as LiDAR and cameras. While current mobile robots can navigate such environments using pre-defined, high-precision maps based on hand-crafted rules catered for the specific environment, they lack commonsense reasoning capabilities, especially the traversability analysis, that most humans possess when navigating unknown outdoor spaces. To address this gap, we introduce the Global Navigation Dataset (GND), a large-scale dataset that integrates multi-modal sensory data, including 3D LiDAR point clouds and RGB and 360° images, as well as multi-category traversability maps (pedestrian walkways, vehicle roadways, stairs, off-road terrain, and obstacles) from ten university campuses. These environments encompass a variety of parks, urban settings, elevation changes, and campus layouts of different scales. The dataset covers approximately$2.7 ~\text{km}^{2}$and includes at least 350 buildings in total. We also present a set of novel applications of GND to showcase its utility to enable global robot navigation, such as map-based global navigation, mapless navigation, and global place recognition. GND's website can be found at https://cs.gmu.edu/xiao/Research/GND/.

Safety concerns surrounding autonomous vehicles (AVs) present significant barriers to their widespread adoption. In AVs, it is necessary to make speedy decisions to safely roam through complex dynamic environments. Interestingly, predicting the future environment can aid in making these early decisions from the partially observed data. This proactive approach is becoming increasingly vital as the number of vehicles on the roads continues to rise, necessitating advanced development strategies for AVs. In this scenario, simulations based on Digital Twin (DT) are proving to be effective in necessary computation during the development and inference phase of the AVs. In fact, the DT system can play a crucial role in making early decisions. Thus, in this research, we propose a Generative Adversarial Network (GAN) enhanced frame prediction system for single and multi-time ahead image forecasting to aid in environment prediction and early decision. We demonstrate the relative motion of entities within the frames and evaluate our system's efficacy through qualitative and quantitative analyses. As This GAN-enhanced system---inside a DT---can predict a few frames into the future and check for anomalies, this can help the AVs make swift decisions. Moreover, by harnessing this capability to create diverse synthetic scenarios, we can enhance the development of the DT system, thus unlocking a multitude of opportunities for training various models for autonomous vehicles (AVs).