Agentic AI, often powered by large language models (LLMs), is becoming increasingly popular and adopted to support autonomous reasoning, decision-making, and task execution across various domains. While agentic AI holds great promise, its deployment as services for easy access raises critical challenges in pricing, due to high infrastructure and computation costs, multidimensional and task-dependent Quality of Service (QoS), and liability concerns in high-stakes applications. In this work, we propose PACT, a Pricing framework for cloud-based Agentic AI services through a Contract-Theoretic approach. PACT models quality of service along both objective and subjective dimensions, while accounting for computational, infrastructure, and liability costs on the provider side. It enables heterogeneous users to select tailored service options that align with their needs. Numerical evaluations demonstrate that PACT ensures 100% QoS alignment between users and providers while offering a scalable and liable approach to pricing agentic AI services.

Leveraging recent advances in wireless communication, IoT, and AI, intelligent transportation systems (ITS) played an important role in reducing traffic congestion and enhancing user experience. Within ITS, navigational recommendation systems (NRS) are essential for helping users simplify route choices in urban environments. However, NRS are vulnerable to information-based attacks that can manipulate both the NRS and users to achieve the objectives of the malicious entities. This study aims to assess the risks of misinformed demand attacks, where attackers use techniques like Sybil-based attacks to manipulate the demands of certain origins and destinations considered by the NRS. We propose a game-theoretic framework for proactive risk assessment of demand attacks (PRADA) and treat the interaction between attackers and the NRS as a Stackelberg game. Specifically, we consider the case of local-targeted attacks, in which the attacker aims to make the NRS recommend the authentic users towards a specific road that favors certain groups. Our analysis unveils the equivalence between users’ incentive compatibility and Wardrop equilibrium recommendations and shows that the NRS and its users are at high risk when encountering intelligent attackers who can significantly alter user routes by strategically fabricating non-existent demands. To mitigate these risks, we introduce a trust mechanism that leverages users’ confidence in the integrity of the NRS, and show that it can effectively reduce the impact of misinformed demand attacks. Numerical experiments are used to corroborate the results and support our discussion of the Resilience Paradox, where locally targeted attacks can sometimes benefit the overall traffic conditions. Our framework not only assists risk assessment in automating the evaluation process and estimating potential impacts but also aligns with standards like ISO/IEC 27005, offering a proactive approach to managing risks in ITS.

AI-driven algorithmic systems are increasingly adopted across various sectors, yet the lack of transparency can raise accountability concerns about claimed privacy protection measures. While machine-based audits offer one avenue for addressing these issues, they are often costly and time-consuming. Herd audit, on the other hand, offers a promising alternative by leveraging collective intelligence from end-users. However, the presence of epistemic disparity among auditors, resulting in varying levels of domain expertise and access to relevant knowledge, captured by the rational inattention model, may impact audit assurance. An effective herd audit must establish a credible accountability threat for algorithm developers, incentivizing them not to breach user trust. In this work, our objective is to develop a systematic framework that explores the impact of herd audits on algorithm developers through the lens of the Stackelberg game. Our analysis reveals the importance of easy access to information and the appropriate design of rewards, as they increase the auditors’ assurance in the audit process. In this context, herd audit serves as a deterrent to negligent behavior. Therefore, by enhancing herd accountability, herd audit contributes to responsible algorithm development, fostering trust between users and algorithms.

Traffic safety risk significantly impacts road users in urban mobility systems, making it important in transportation management decision-making. Current mobility management strategies predominantly focus on macro-level monitoring through traffic sensing infrastructure, and struggle to capture network-wide, real-time safety risks due to the limited spread of vehicle-based sensors. To address this, we propose a Digital Twin-based Driver Risk-aware Predictive Mobility Analytics (DT-DIMA) system. The DT-DIMA system integrates real-time traffic information from pan-tilt-cameras (PTCs), synchronizes this data into a digital twin to accurately replicate the physical world, and predicts network-wide mobility and safety risks in real time. The system’s innovation lies in its integration of spatial-temporal modeling, simulation, and online control modules. Tested and evaluated under normal traffic conditions and incidental situations (e.g., unexpected accidents, pre-planned work zones) in a simulated testbed in Brooklyn, New York, DT-DIMA demonstrated mean absolute percentage errors (MAPEs) ranging from 9.40% to 13.12% in estimating network-level traffic volume and MAPEs from 2.12% to 12.97% in network-level safety risk prediction. In addition, the highly accurate safety risk prediction enables PTCs to preemptively monitor road segments with high driving risks before incidents take place. Such proactive PTC surveillance creates around a 5-minute lead time in capturing traffic incidents. The DT-DIMA system enables transportation managers to understand mobility not only in terms of traffic patterns but also driver-experienced safety risks, allowing for proactive resource allocation in response to various traffic situations.

Misinformation has become a growing issue on online social platforms (OSPs), especially during elections or pandemics. To combat this, OSPs have implemented various policies, such as tagging, to notify users about potentially misleading information. However, these policies are often trans-parent and therefore susceptible to being exploited by content creators, who may not be willing to invest effort into producing authentic content, causing the viral spread of misinformation. Instead of mitigating the reach of existing misinformation, this work focuses on a solution of prevention, aiming to stop the spread of misinformation before it has a chance to gain mo-mentum. We propose a Bayesian persuaded branching process$(\text{BP}^{2})$to model the strategic interactions among the OSP, the content creator, and the user. The misinformation spread on OSP is modeled by a multi-type branching process, where users' positive and negative comments influence the misinformation spreading. Using a Lagrangian induced by Bayesian plausibility, we characterize the OSP's optimal policy under the perfect Bayesian equilibrium. The convexity of the Lagrangian implies that the OSP's optimal policy is simply the fully informative tagging policy: revealing the content's accuracy to the user. Such a tagging policy solicits the best effort from the content creator in reducing misinformation, even though the OSP exerts no direct control over the content creator. We corroborate our findings using numerical simulations.

Deep learning (DL) applications have attracted significant attention with the rapidly growing demand for Internet of Things (IoT) systems. However, performing the inference tasks for DL applications on IoT devices is challenging due to the large computational demands of DL models. Recently, edge computing has offered us a solution by deploying resources near the end users. However, resources at the edge are still limited; thus, management issues, such as allocating the networking resources as well as the computing capabilities and configuring the devices appropriately for different applications, become essential. For knobs in such edge management, we consider multiple application tasks with different options of DL models and different hyperparameter settings, along with possible decomposition points that utilize the split DL concept to design the configuration tables. Layer-level decomposition in split DL provides greater flexibility by splitting a single DL inference model into parts on different computing devices, and each part consists of several consecutive layers. We then propose the SplitDL-Image and the SplitDL-Video algorithms based on the Vickrey–Clarke–Groves (VCG) mechanism by considering model performance and frames per second (FPS) requirements with the preferences of the heterogeneous IoT devices. The proposed method allocates networking and edge server computing resources according to the designed configuration tables by assigning the appropriate configuration to each IoT device. Simulation results based on real-world applications show that the proposed method indeed allocates more resources to IoT devices with more urgent/important tasks, preference for better accuracy, or higher local computational cost. In addition, other desired properties, such as truthful bidding, individual rationality, and weakly budget balance, are also guaranteed.

Recently, an increasing amount of application tasks have depended on deep learning (DL) inference models on Internet of Things (IoT) based camera networks. However, it is challenging to perform the inference of such resource-hungry DL models on the computationally limited IoT system. Compared to cloud computing, edge computing deploys resources near the end-users to reduce the transmission delay and retains the raw data on the trusted servers to mitigate privacy concerns. Since resources at the edge are limited, management like user association decisions, edge resources allocation, and device configuration with DL model parameter selection becomes essential. This work proposes a coalition formation game-based algorithm to solve the association problem between IoT-based cameras and the edge nodes. Our goal is to maximize the social welfare that consists of multi-view detection enhancement, the privacy retained preference, and the power savings from the cameras. Besides, we adopt the concept of split-ML to provide more flexibility for networking and computing resources allocation at the edge. The final coalition structure is proved to converge and maintain stability. The simulation results show that each design knob, including association decisions made by coalition formation, DNN layer-level partition, and multi-view detection, is essential under different scenario settings.

With the rapid growth in the demand for internet-of-things (IoT) systems such as factory of future, smart home, smart city, long-term healthcare, deep learning (DL) applications have attracted significant attention from people. However, it is challenging to inference such tasks on computational limited IoT devices due to the massive computational requirements of DL models. The conventional solution is to deliver data collected from IoT devices to remote cloud for computation, while this may not only rely heavily on networking resources but also cause security risks. The rising concept of edge computing gives us another solution. Tasks can be decomposed by different scales. Model-level decomposition is to inference the models in the task pipeline on different computing devices, while layer-level decomposition is to inference the layers in the single DL model on different computing devices. Both scales of decomposition can be inferenced on edge-cloud framework or simply device-edge framework based on different considerations. This would lead to several aspects of management: resource management for both networking resources and computing resources as well as application configuration management. In this work, we first design configuration tables for different application tasks, with different choices of DL models, different parameter settings, and different layer-level partition points, then we apply Vick-rey-Clarke-Groves (VCG) auction to allocate both networking and computing resources by assigning each IoT device a proper configuration. We also show some desired properties such as truthfulness of the mechanism and observe that the VCG truly utilizes both resources better.

In this paper, we have developed a real-time interactive social learning platform (ISLP) for higher education. The objective is to enhance interactive learning and accumulate knowledge for worldwide dissemination and idea sharing. ISLP combines the features of real-time recoding, synchronized broadcasting, note taking, and interactive timeline for interactive feedback and collaborative learning. The teaching and learning activities could be broadcast across different locations in time and space through use of the proposed platform.

Frame rate up-conversion is a postprocessing tool to convert the frame rate from a lower number to a higher one. It is a useful technique for a lot of practical applications, such as display format conversion, low bit rate video coding and slow motion playback. Unlike traditional approaches, such as frame repetition or linear frame interpolation, motion-compensated frame interpolation (MCFI) technique is more efficient since it takes block motion into account. In this paper, by considering the deficiencies of previous works, new criteria and coding schemes for improving motion derivation and interpolation processes are proposed. Next, for video coding applications, adaptive frame skip is executed at the encoder side to maximize the power of MCFI so that the quality of interpolated frames is guaranteed. Experimental results show that our proposal effectively enhances the overall quality of the frame rate up-converted video sequence, both subjectively and objectively.