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.

The rise of multi-modal, multi-node foundation models has revolutionized intelligent IoT sensing systems by enabling general-purpose inference from distributed sensing sources to support diverse downstream applications. However, the high communication cost of transmitting raw sensor data from distributed nodes to a central inference model remains a critical bottleneck, particularly in bandwidth- or energy-constrained environments. While existing compression methods can reduce data volume, they often lack the adaptability needed to handle variations in data relevance and redundancy across sources, modalities, and time. To address this challenge, we introduce ZipFM, a lightweight, plug-and-play middleware that dynamically configures sensor data compression strategies on a per-node, per-modality, and per-time-step basis to minimize network traffic while preventing model degradation, taking model sensitivity to different data sources into account. ZipFM is (i) compatible with different pre-trained foundation models without requiring access to their internal mechanisms or retraining, (ii) agnostic to the underlying tools available for data compression, and (iii) independent of the specific downstream inference tasks performed. At its core, ZipFM uses the compression-induced latent representation shift, produced by the foundation model's backbone, as a proxy for downstream accuracy degradation, and enforces a system-wide optimal representation shift (in the sense of minimizing compression-related degradation) through a lightweight feedback control mechanism. Experiments on three real-world IoT sensing datasets demonstrate that ZipFM significantly reduces communication costs while preserving model performance.

Many traditional feedback-based beamforming techniques can pose risks in environments where adversaries try to jam or detect the beamforming agents. Several low- or no-feedback approaches to beamforming have been proposed to remedy this. Still, problems such as limited transmitter power budgets and inaccurate Channel State Information (CSI) complicate this problem. To that end, this work investigates the use of constrained optimization techniques to allow a team of distributed Unmanned Ground Vehicles (UGVs) to form a beam in the absence of feedback without accurate knowledge of CSI. Specifically, we tune each transmitting agent's signal amplitude and phase offset to selectively build higher-power beams at allied receivers and lower-power nulls at adversarial receivers. To achieve this, we implement a decentralized version of the Frank-Wolfe algorithm, which does not rely on a central coordinator to solve the optimal signal amplitudes and phase offsets without accurate CSI measurements. Numerical results are also provided to validate our approach.

Autonomous platforms are confronted by a diversity of challenges in unstructured environments, which make monitoring performance a non-trivial task. Some of these environments are so complex that they preclude persistent, nearby operator oversight. This absence of oversight motivates the need for an online monitoring system, specifically for robots operating in difficult environments. We develop a test methodology and set of online monitoring metrics by extending methods for characterizing robotic-systems using offline metrics. We implement this test methodology in an unstructured, outdoor environment and show the resulting performance information gained from our online monitoring solution. This online monitoring approach is generalizable such that it characterizes any robotic system that meets our set of hardware and software criteria.

We consider the combined problem of frontier exploration in a complex indoor environment while seeking a radio source. To do this in an efficient manner, we incorporate radio signal strength (RSS) information into the exploration algorithm by locally sampling the RSS and estimating the 2-D RSS gradient. The algorithm exploits the local motion to collect RSS samples for gradient estimation and seeks to explore in a way that brings the robot to the signal source. This strategy avoids random or exhaustive exploration. An indoor experiment demonstrates the exploration algorithm that uses this information to dynamically prioritize candidate frontiers and traverse to a radio source. Simulations, including radio propagation modeling with a ray-tracing algorithm, enable study of control algorithm tradeoffs and statistical performance.