The Metaverse represents a transformative shift beyond traditional mobile Internet, creating an immersive, persistent digital ecosystem where users can interact, socialize, and work within 3D virtual environments. Powered by large models such as ChatGPT and Sora, the Metaverse benefits from precise large-scale real-world modeling, automated multimodal content generation, realistic avatars, and seamless natural language understanding, which enhance user engagement and enable more personalized, intuitive interactions. However, challenges remain, including limited scalability, constrained responsiveness, and low adaptability in dynamic environments. This paper investigates the integration of large models within the Metaverse, examining their roles in enhancing user interaction, perception, content creation, and service quality. To address existing challenges, we propose a generative AI-based framework for optimizing Metaverse rendering. This framework includes a cloud-edge-end collaborative model to allocate rendering tasks with minimal latency, a mobility-aware pre-rendering mechanism that dynamically adjusts to user movement, and a diffusion model-based adaptive rendering strategy to fine-tune visual details. Experimental results demonstrate the effectiveness of our approach in enhancing rendering efficiency and reducing rendering overheads, advancing large model deployment for a more responsive and immersive Metaverse.

Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

Driven by recent advances of large models and agents, embodied artificial intelligence (AI) emerges as a transformative paradigm for next-generation AI, endowing agents with physical forms and the ability to perceive, reason, and act within real-world environments. Unlike disembodied or virtual AI agent systems, embodied agents co-evolve cognition, control, and embodiment through continuous feedback loops, enabling applications ranging from humanoid robots to autonomous vehicles. In this survey, we first introduce a dual-brain architecture of embodied AI and examine its foundational technologies and key characteristics. We then analyze the security and privacy landscape, identifying critical vulnerabilities and evaluating existing/potential countermeasures. Finally, we outline emerging trends and open research directions in this emerging field, charting a roadmap toward efficient, secure, and ethically aligned embodied AI ecosystems.

Deep reinforcement learning (DRL) has been implemented across various critical applications, including smart grids, trac management systems, and autonomous vehicles. To safeguard intellectual property and mitigate security vulnerabilities, access to DRL models is typically restricted to a black-box format. is means specic details like the structure of the policy network and optimization processes are not openly available to users. It is crucial to determine if the hyper-parameters can be inferred from observable states and actions within these models, presenting two primary challenges: 1) limited data available from the black-box model and 2) the intertwined eects of hyperparameters on the model's behavior. Since DRL models exhibit varying behaviors in identical tasks depending on their hyper-parameter congurations, we introduce a novel hyper-parameter inference attack against DRL, named HyperInfer, which allows adversaries to deduce the settings of a black-box DRL model. In order to fully assess the risk of model hyper-parameter leakage, we design two novel state generation methods that provoke divergent responses from DRL models. We also develop an inference framework to elucidate the relationship between model behavior and hyper-parameter settings. rough comprehensive experiments involving multiple DRL models and environments, we demonstrate that model behaviors can indeed reveal hyper-parameter settings, with inference accuracy surpassing 90% in scenarios such as PPO with CartPole. We also discuss keyndings relevant to practical applications and explore how knowledge of hyperparameters can facilitate more sophisticated attacks. Lastly, we propose potential defensive strategies to minimize the risk of hyper-parameter leakage in DRL models.

Recommender systems predict and suggest relevant options to users in various domains, such as e-commerce, streaming services, and social media. Recently, deep reinforcement learning (DRL)-based recommendation systems have become increasingly popular in academics and industry since DRL can characterize the long-term interaction between the system and users to achieve a better recommendation experience, e.g., Netflix, Spotify, Google, and YouTube. This paper demonstrates that an adversary can manipulate the DRL-based recommender system by injecting carefully designed user-system interaction records. The poisoning attack against the DRL-based recommender system is formulated as a non-convex integer programming problem. To solve the problem, we proposed a three-phase mechanism (called PARL) to maximize the hit ratio (the proportion of recommendations that result in actual user interactions, such as clicks, purchases, or other relevant actions) while avoiding easy detection. The core idea of PARL is to improve the ranking of the target item while fixing the rankings of other items. Considering the sequential decision-making characteristics of DRL, PARL rearranges the items' order of the fake users to mimic the normal users' sequential features, an aspect usually overlooked in existing work. Our experiments on three real-world datasets demonstrate the effectiveness of PARL and better concealment against the detection techniques. PARL is open-sourced at https://github.com/PARL-RS/PARL.

Although previous studies have extensively explored the relationship between urban green spaces and residents’ well-being, research on how nature-based sports venues enhance urban well-being through multiple emotional mechanisms remains relatively limited. Drawing on environmental psychology, place attachment theory, and the principles of biophilic design, this study constructs a dual-mediation model incorporating Connectedness to Nature (CN) and Place Attachment (PA) to examine the pathways through which natural design features—including Natural Visibility (NV), Spatial Integration (SI), and Human–Nature Interactivity (HNI)—influence individuals’ urban well-being. Using ten representative nature-integrated sports venues in China as research sites, a total of 856 valid questionnaires were collected, and structural equation modeling (SEM) was applied for empirical analysis. The results show that (1) NV, SI, and HNI all exert significant positive effects on CN and PA; (2) CN significantly promotes both PA and Urban Well-being (UWB); (3) PA has a significant positive effect on UWB; and (4) both CN and PA serve as significant mediators between natural design features and UWB, with an evident serial mediation effect from CN to PA. These findings reveal the multilayered psychological mechanisms through which nature-based sports venues enhance residents’ well-being, enrich the theoretical framework of nature-oriented design and urban sustainability, and provide empirical evidence for the health-oriented and emotion-responsive design of urban sports facilities.