With the rapid advancement of large models (LMs), the development of general-purpose intelligent agents powered by LMs has become a reality. It is foreseeable that in the near future, LM-driven general AI agents will serve as essential tools in production tasks, capable of autonomous communication and collaboration without human intervention. This paper investigates scenarios involving the autonomous collaboration of future LM agents. We review the current state of LM agents, the key technologies enabling LM agent collaboration, and the security and privacy challenges they face during cooperative operations. To this end, we first explore the foundational principles of LM agents, including their general architecture, key components, enabling technologies, and modern applications. We then discuss practical collaboration paradigms from data, computation, and knowledge perspectives to achieve connected intelligence among LM agents. After that, we analyze the security vulnerabilities and privacy risks associated with LM agents, particularly in multi-agent settings, examining underlying mechanisms and reviewing current and potential countermeasures. Lastly, we propose future research directions for building robust and secure LM agent ecosystems.
20 October 2025 in IEEE Transactions on Cognitive Communications and Networking
With the rapid proliferation of large language models and vision‑language models, AI agents have evolved from isolated, task‑specific systems into autonomous, interactive entities capable of perceiving, reasoning, and acting without human intervention. As these agents proliferate across virtual and physical environments, from virtual assistants to embodied robots, the need for a unified, agent‑centric infrastructure becomes paramount. In this survey, we introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale. We begin by presenting a general IoA architecture, highlighting its hierarchical organization, distinguishing features relative to the traditional Internet, and emerging applications. Next, we analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict‑resolution mechanisms, and incentive models. Finally, we identify open research directions toward building resilient and trustworthy IoA ecosystems.
16 July 2025 in IEEE Open Journal of the Computer Society
With the rise of large language and vision-language models, AI agents have evolved into autonomous, interactive systems capable of perception, reasoning, and decision-making. As they proliferate across virtual and physical domains, the Internet of Agents (IoA) has emerged as a key infrastructure for enabling scalable and secure coordination among heterogeneous agents. This survey offers a comprehensive examination of the security and privacy landscape in IoA systems. We begin by outlining the IoA architecture and its distinct vulnerabilities compared to traditional networks, focusing on four critical aspects: identity authentication threats, cross-agent trust issues, embodied security, and privacy risks. We then review existing and emerging defense mechanisms and highlight persistent challenges. Finally, we identify open research directions to advance the development of resilient and privacy-preserving IoA ecosystems.
2 October 2024 in IEEE/ACM Transactions on Networking
A key feature of federated learning (FL) is to preserve the data privacy of end users. However, there still exist potential privacy leakage in exchanging gradients under FL. As a result, recent research often explores the differential privacy (DP) approaches to add noises to the computing results to address privacy concerns with low overheads, which however degrade the model performance. In this paper, we strike the balance of data privacy and efficiency by utilizing the pervasive social connections between users. Specifically, we propose SCFL, a novel S ocial-aware C lustered F ederated L earning scheme, where mutually trusted individuals can freely form a social cluster and aggregate their raw model updates (e.g., gradients) inside each cluster before uploading to the cloud for global aggregation. By mixing model updates in a social group, adversaries can only eavesdrop the social-layer combined results, but not the privacy of individuals. As such, SCFL considerably enhances model utility without sacrificing privacy in a low-cost and highly feasible manner. We unfold the design of SCFL in three steps. i) Stable social cluster formation. Considering users’ heterogeneous training samples and data distributions, we formulate the optimal social cluster formation problem as a federation game and devise a fair revenue allocation mechanism to resist free-riders. ii) Differentiated trust-privacy mapping. For the clusters with low mutual trust, we design a customizable privacy preservation mechanism to adaptively sanitize participants’ model updates depending on social trust degrees. iii) Distributed convergence. A distributed two-sided matching algorithm is devised to attain an optimized disjoint partition with Nash-stable convergence. Experiments on Facebook network and MNIST/CIFAR-10 datasets validate that our SCFL can effectively enhance learning utility, improve user payoff, and enforce customizable privacy protection.
The rapid development of large models such as GPT-4 and Midjourney has spawned worldwide attention in various fields. To practically deploy large model services in downstream tasks, cloud-edge collaboration mechanism offers an appealing solution by seamlessly sharing fresh data, knowledge, and resources between the cloud and distributed edge nodes. Offloading the fine-tuning process of large models to edge networks through federated learning (FL) to implement efficient and privacy-preserving large model services has become an emerging research direction. However, there exist challenges in terms of privacy leakages, data heterogeneity, and edge resource constraints in delivering cloud-edge collaborative large model services. In this paper, we propose an innovative cloud-edge collaborative framework for federated large model training and deployment with reduced communication overheads and enhanced scalability. Within this framework, we further devise a data-model-driven privacy protection mechanism, a lightweight reciprocal knowledge transfer approach, and an optimal and reliable edge node recruitment strategy to fully harness edge data/knowledge/resources with enhanced privacy protection under high heterogeneity. Through an experimental case study, we validate the effectiveness of the proposed framework and solutions. Finally, we outline significant future research directions in this evolving field.