Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler that allows distributed LLM agents to co-train an intelligent global LLM without centralizing local datasets. However, the FFT-enabled IoA systems remain vulnerable to model poisoning attacks, where adversaries can upload malicious updates to the server to degrade the performance of the aggregated global LLM. This paper proposes a graph representation-based model poisoning (GRMP) attack, which exploits overheard benign updates to construct a feature correlation graph and employs a variational graph autoencoder to capture structural dependencies and generate malicious updates. A novel attack algorithm is developed based on augmented Lagrangian and subgradient descent methods to optimize malicious updates that preserve benign-like statistics while embedding adversarial objectives. Experimental results show that the proposed GRMP attack can substantially decrease accuracy across different LLM models while remaining statistically consistent with benign updates, thereby evading detection by existing defense mechanisms and underscoring a severe threat to the ambitious IoA paradigm.

In child-centered design, directly engaging children is crucial for deeply understanding their experiences. However, current research often prioritizes adult perspectives, as interviewing children involves unique challenges such as environmental sensitivities and the need for trust-building. AI-powered virtual humans (VHs) offer a promising approach to facilitate engaging and multimodal interactions with children. This study establishes key design guidelines for LLM-powered virtual humans tailored to child interviews, standardizing multimodal elements including color schemes, voice characteristics, facial features, expressions, head movements, and gestures. Using ChatGPT-based prompt engineering, we developed three distinct Human-AI workflows (LLM-Auto, LLM-Interview, and LLM-Analyze) and conducted a user study involving 15 children aged 6 to 12. The results indicated that the LLM-Analyze workflow outperformed the others by eliciting longer responses, achieving higher user experience ratings, and promoting more effective child engagement.

As the most popular low-power communication protocol, cybersecurity research on Bluetooth Low Energy (BLE) has garnered significant attention. Due to BLE’s inherent security limitations and firmware vulnerabilities, spoofing attacks can easily compromise BLE devices and tamper with privacy data. In this paper, we proposed BLEGuard, a hybrid detection mechanism combined cyber-physical features with learning-based techniques. We established a physical network testbed to conduct attack simulations and capture advertising packets. Four different network features were utilized to implement detection and classification algorithms. Preliminary results have verified the feasibility of our proposed methods.

As the foremost protocol for low-power communication, Bluetooth Low Energy (BLE) significantly impacts various aspects of our lives, including industry and healthcare. Given BLE's inherent security limitations and firmware vulnerabilities, spoofing attacks can readily compromise BLE devices and jeopardize privacy data. In this paper, we introduce BLEGuard, a hybrid mechanism for detecting spoofing attacks in BLE networks. We established a physical Bluetooth system to conduct attack simulations and construct a substantial dataset (BLE-SAD). BLEGuard integrates pre-detection, reconstruction, and classification models to effectively identify spoofing activities, achieving an impressive preliminary accuracy of 99.01%, with a false alarm rate of 2.05% and an undetection rate of 0.36%.