Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

As Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, it also brings underexplored safety risks.Its decentralized architecture, which separates clients and servers, poses unique challenges for systematic safety analysis.This paper proposes a novel framework to enhance MCP safety.Guided by the MAESTRO framework, we first analyze the missing safety mechanisms in MCP, and based on this analysis, we propose the Model Contextual Integrity Protocol (MCIP), a refined version of MCP that addresses these gaps.Next, we develop a fine-grained taxonomy that captures a diverse range of unsafe behaviors observed in MCP scenarios.Building on this taxonomy, we develop benchmark and training data that support the evaluation and improvement of LLMs' capabilities in identifying safety risks within MCP interactions.Leveraging the proposed benchmark and training data, we conduct extensive experiments on state-of-the-art LLMs.The results highlight LLMs' vulnerabilities in MCP interactions and demonstrate that our approach substantially improves their safety performance.1

Haoran Li, Wei Fan, Yulin Chen, Cheng Jiayang, Tianshu Chu, Xuebing Zhou, Peizhao Hu, Yangqiu Song. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Decision tree and its generalization of random forests are a simple yet powerful machine learning model for many classification and regression problems. Recent works propose how to privately evaluate a decision tree in a two-party setting where the feature vector of the client or the decision tree model (such as the threshold values of its nodes) is kept secret from another party. However, these works cannot be extended trivially to support the outsourcing setting where a third-party who should not have access to the model or the query. Furthermore, their use of aninteractivecomparison protocol does not support branching program, hence requires interactions with the client to determine the comparison result before resuming the evaluation task. In this paper, we propose the first secure protocol for collaborative evaluation of random forests contributed by multiple owners. They outsource evaluation tasks to a third-party evaluator. Upon receiving the client's encrypted inputs, the cloud evaluates obliviously on individually encrypted random forest models and calculates the aggregated result. The system is based on our new secure comparison protocol, secure counting protocol, and a multi-key somewhat homomorphic encryption on top of symmetric-key encryption. This allows us to reduce communication overheads while achieving round complexity lower than existing work.

Virtualization is a promising technology that has facilitated cloud computing to become the next wave of the Internet revolution. Adopted by data centers, millions of applications that are powered by various virtual machines improve the quality of services. Although virtual machines are well-isolated among each other, they suffer from redundant boot volumes and slow provisioning time. To address limitations, containers were born to deploy and run distributed applications without launching entire virtual machines. As a dominant player, Docker is an open-source implementation of container technology. When managing a cluster of Docker containers, the management tool, Swarmkit, does not take the heterogeneities in both physical nodes and virtualized containers into consideration. The heterogeneity lies in the fact that different nodes in the cluster may have various configurations, concerning resource types and availabilities, etc., and the demands generated by services are varied, such as CPU-intensive (e.g. Clustering services) as well as memory-intensive (e.g. Web services). In this paper, we target on investigating the Docker container cluster and developed, DRAPS, a resource-aware placement scheme to boost the system performance in a heterogeneous cluster.

Opportunistic network created among mobile devices in challenged environments can be effectively exploited to provide application services. However, data and services may be subject to space and time constraints in challenged environments where it is critical to complete application services within given spatiotemporal limits. This paper discusses an analytical framework that takes into account human mobility traces and provides quantitative measures of the spatiotemporal requirements for service sharing and composition in challenged opportunistic environments. The analytical results provide estimates on feasibility of service sharing and service compositions for various mobility models. To validate the framework, we conduct simulation experiments using multiple human mobility and synthesized datasets. In these experiments, we analyze service composition feasibility, service completion rate and time for resource utilization.

Geosocial applications collect (and record) users' precise location data to perform proximity computations, such as notifying a user or triggering a service when a friend is within geographic proximity. With the growing popularity of mobile devices that have sophisticated localization capability it becomes more convenient and tempting to share location data. But the precise location data in plaintext not only exposes user's whereabouts but also mobility patterns that are sensitive and cannot be changed easily. This paper proposes cryptographic protocols on top of spatial cloaking to reduce the resolution of location and balance between data utility and privacy. Specifically we interest in the setting that allows users to send periodic updates of precise coordinates and define privacy preferences to control the granularity of the location, both in an encrypted format. Our system supports three kinds of user queries --- "Where is this user?", "Who is nearby?", and "How close is this user from another user?". Also, we develop a new algorithm to improve the multidimensional data access by reducing significant masking error. Our prototype and various performance evaluations on different platforms demonstrated that our system is practical.

In this paper, we study the power allocation problem for the downlink transmission in a set of closed-access femtocells which underlay a number of macrocells. We introduce a mutli-step pricing mechanism for the macrocells to control the cross- tier interference by femtocell transmissions without explicit coordination. We model the cross- tier joint power allocation process in the heterogeneous network as a non-cooperative, average-reward Markov game. By investigating the structure of the instantaneous payoff functions in the game, we propose a self-organized strategy learning scheme based on learning automata for both the macrocell base stations and the femtocell access points to adapt their transmit power simultaneously. We prove that the proposed learning scheme is able to find a pure-strategy Nash equilibrium of the game without the need for the femtocell access points to share any local information. Simulation results show the efficiency of the proposed learning scheme.

Opportunistic networks are characterized by the dynamic connectivity created when mobile devices encounter each other, as they are within close proximity. During these transient opportunities, devices are typically within one-hop wireless range of their neighbors. Opportunistic networks are an effective way, in terms of bandwidth and battery consumption to distribute large volume content among peers. Many existing proposals consider opportunistic networks as a best-effort content delivery approach, which limits their applications. We exploit characteristics of human mobility to derive an effective data forwarding scheme that achieves Combined Optimal Stability and Capacity (COSC) for opportunistic networks. COSC includes a path selection algorithm to maximize the utility of link capacity and stability. We validate theoretical findings with rigorous simulation studies using synthetic and real-world mobility traces. When compared with other approaches, COSC shows significant improvement due to the consideration of link capacity and stability.

The rapid adoption of mobile phones and growing number of mobile services (like Whatsapp) have created high volume of mobile data traffic. Compared to the traditional voice and SMS services, mobile data is becoming more and more important. Bandwidth is in high demand and is becoming critical for user experiences with mobile contents. Due to a variety of factors (such as admission control policies, signal fading), bandwidth available to a device cannot be directly mapped to the signal strength. This creates a need for bandwidth estimation on mobile phones, similar to the signal strength indicator, to show the estimated bandwidth at the instant. Due to the complexity of bandwidth measurement and/or limitations of earlier generations of mobile phones, there is a small amount of research on bandwidth estimation for mobile phones. This paper revisits a variety of bandwidth estimation methods for wireless and mobile networks, analyses why most of the solutions fail, studies the accuracy limitation of bandwidth estimation in mobile networks, and finds a feasible solution for dynamically estimating bandwidth on mobile phones. We propose GPing-Pair, a low-cost bandwidth approximation for cellular connections that estimates bandwidth on the mobile device without server support. We implemented the proposed method as an application for Android phones.

The number of mobile users of on demand video is growing rapidly. However, bandwidth fluctuation in the 3G/LTE technologies is an obstacle in providing high quality smooth video playout for users on the go. In this paper, we present ColStream that can aggregate bandwidth from ubiquitous devices to ensure high quality video streaming with minimal stalling time. ColStream dynamically adjusts the set of collaborators and the size of video chunks that the collaborators need to pre-fetch ahead of the video chunks playout time to provide smooth video playout. ColStream uses a multi-objective optimisation method to maximise bandwidth and minimise cost. ColStream requires neither external servers nor proxies to provide its functionality. The paper describes the ColStream functionality, architecture, applied algorithms, ColStream prototype, and evaluation of its suitability for effective video streaming in mobile environments.

In typical wireless networks, end-to-end routing is a usual way to deliver data packets from source nodes to destination nodes. In the case of link failures when no alternative route is found, the routing protocols will drop these packets. As a way to improve the packet delivery ratio, an integration of the store-carry-forward features with the traditional end-to-end communication has been already proposed. The existing solutions propose one-time only switching from one communication mode to another should the link failures occur. In this paper, we propose a hybrid protocol to support the dynamic switch between the two modes of communication should the link conditions changed. That is, the protocol utilises the ability to buffer packets when end-to-end routes are not possible, and leverages the end-to-end routes whenever they become available to ensure performance. We evaluate the proposed protocol using a set of comprehensive simulation scenarios to systematically demonstrate its significant improvement in packet delivery over one of the best representative routing protocol for end-to-end routing.

Many wireless network protocols and algorithms rely on estimations of the link capacity in order to make informed decisions on routing data packets, selection of the optimal transmission rate, flow and admission control. In this paper we present an investigation into our Effective Link Capacity (ELC) metric which combines the use of MAC layer monitoring with knowledge of the network timing specifications to provide an accurate model of link conditions. We subject the resulting metric to an experimental investigation across a range of conditions using a conducted testbed. We demonstrate that commodity wireless devices do not conform to the IEEE 802.11 specification, thus making modeling difficult. Given that ELC and the IEEE 802.11s Airtime link metric are directly related, we compare their accuracy in estimating the link capacity. We demonstrate that ELC significantly outperforms two widely-used implementations of Airtime.

This paper presents a practical and low-cost approach to estimate the maximum achievable wireless link bandwidth based on the prevailing link conditions in an IEEE 802.11 network. This approach works by observing the number of bits successfully delivered over a link, divided by the corresponding channel occupancy time. The method is passive and does not introduce any extra overhead on the channel, and is based on the timing model of the IEEE 802.11 MAC layer. All required parameters are obtained locally at the sending node from the MAC layer. We evaluate the accuracy of the proposed method via a full implementation and experiments on our conducted testbed, which provides a more controlled environment and increased repeatability of experiments, compared to over-the-air wireless testbeds. The experiment results show that our method can accurately estimate the link bandwidth with both saturated and low traffic load across links with different transmission rates and link qualities. In addition, results also show that our method is able to track the link bandwidth as its link quality changes.

Node mobility, signal fading and interference introduce dynamics in wireless channels. In 802.11 wireless networks, there are several transmission rates that can be adaptively selected by the MAC-layer rate control mechanisms to cater for various channel conditions. Accurately estimating the current channel conditions and successfully selecting the appropriate rates at the right time is critical to ensure the network's optimal performance. In this paper we focus on the problem of rate selection and present a robust, yet practical, rate control mechanism-RCELC, which measures the throughput achieved by each rate, and it selects a rate that achieve the highest throughput for the current channel conditions. To ensure its robustness RCELC optimises rate sampling and also guarantees achieving the highest throughput even in the cases of collisions. RCELC is a practical rate control mechanism that we have developed and evaluated on new mac80211 framework in Linux. We use a set of comprehensive evaluation scenarios and show that RCELC achieves superior performance and substantially outperforms the best rate control mechanism currently available in Linux.

The ability to accurately estimate wireless link quality is critical to the performance of routing protocols and rate adaptation algorithms in wireless mesh networks. Current link quality estimation methods utilize the packet delivery ratio (PDR) measurement of periodic broadcast probes sent at the lowest transmission rate. However, the estimated link quality does not readily translate to the performance of unicast data traffic at higher transmission rates. In this paper, we propose the use of a measurement-based signal-to-noise ratio (SNR) model to estimate wireless link quality in terms of its PDR performance. Using broadcast traffic measurements at the lowest transmission rate, we construct an "SNR profile'' that characterizes the relationship between the PDR metric and the SNR values computed at a node. We show how we can use the SNR profile to predict the PDR performance at different transmission rates. More importantly, we argue that the frame delivery ratio (FDR) at the MAC layer is a better link quality metric compared to PDR, and show that our proposed approach can use an SNR profile generated with broadcast traffic, to accurately estimate the FDR performance of unicast data traffic at different transmission rates. This then allows us to also accurately estimate the maximum achievable throughput of the wireless link at those rates.

In 802.11-based wireless networks, the ability to accurately predict the impact of interference via the use of an interference model is essential to better and more efficient channel assignment algorithms and data routing protocols. Recently, there have been several works that proposed new interference models utilizing the well-known concept of signal-to-interference-plus-noise ratio (SINR). Using active measurements, these models construct a profile that maps either the measured received signal strength (RSS) or the computed SNR or SINR values at a receiver, to its packet delivery ratio (PDR) performance. The profile is then used by the models to predict the PDR performance in more complex scenarios involving multiple interferers. While comparison with other basic models (e.g. hop-based and distance-based) have been made in these works, there has as yet been no comprehensive comparison on the accuracy of these measurement-based SINR interference models. In this paper, we systematically evaluate the performance of three measurement-based SINR interference models in predicting the interference impact on the successful reception of packets. Our evaluations cover various interference scenarios with both 802.11 and non-802.11 interferers, in experiments carried out in both our conducted testbed and an over-the-air testbed. Our results show that an interference model that utilizes an SINR profile can accurately predict the PDR performance with a maximum root-mean-square error (RMSE) of 10.8% across all our evaluations. In contrast, interference models that rely on the SNR profile and the RSS profile perform poorly, with a maximum RMSE of 61.7% and 66.1% respectively.

Interference is a crucial factor that impacts the overall throughput performance of IEEE 802.11-based wireless networks. As such, understanding interference characteristics is essential towards the optimal management and operation of these networks. In this paper, we use a conducted testbed (that allows us to completely control the signal propagation and received signal strength) to systematically evaluate the impact of interference in terms of the carrier-sensing interference and the receiver interference. Our results show that carrier-sensing interference does not conform to the often-used binary model of "either carrier-sense or no carrier-sense", and that the sum of the normalized sending rates of nodes that can fully carrier-sense each other is greater than 1.0. In terms of receiver interference, our results show that while the interference impact on a data link's throughput is approximately linear with respect to the offered load of the interferer node, its relationship with respect to the offered load of the data sender is non-linear. Our results also show that the combined interference impact of multiple interferer nodes cannot be predicted by just using independent measurements of the interference impact of individual interferer nodes. The results in this paper indicate that commonly made underlying assumptions of interference models are not valid, and consequently show the limitations of the corresponding models.

The 802.11 wireless networking standard has several transmission rates which can be adaptively selected by the MAC layer to cater for various channel conditions. Such dynamic adaptations can improve per-hop performance in wireless networks by enhancing the data throughput, reducing the channel usage time and decreasing the number of failed transmissions. This in turn has an impact on the quality of service (QoS) provided for communicating applications. The new mac80211 framework, which is now part of the Linux operating system, defines functionalities and interfaces that can be used by wireless network drivers to access physical-layer information which has impact on high-level protocols/algorithms. In this paper we present a comprehensive evaluation of the per-hop performance of two rate control mechanisms used by the mac80211 framework in Linux: Minstrel and PID. The evaluation results show that Minstrel outperforms PID. We discuss the PID's performance problems and propose an enhancement to PID to address them. The evaluation of the enhancement confirms substantial improvement of PID's performance in a range of conducted and over-the-air communication scenarios.

The 802.11 standards specify several transmission rates that can be used at the MAC layer protocol to adapt the transmission rate to channel conditions. Such dynamic adaptations can improve per-hop performance in Wireless Networks and therefore can have impact on the Quality of Service provided for communicating applications. In this paper we present a comprehensive evaluation of the performance of four rate control mechanisms used by the MadWifi driver in Linux: Onoe, AMRR, SampleRate and minstrel. The evaluation of these four rate control mechanisms was carried out in our platform for controllable and repeatable experiments.

This paper presents the results of an independent evaluation of four different commercial wireless mesh network systems using IEEE 802.11 radios in the context of small-scale, rapid deployment scenarios in public safety and emergency applications. To ensure repeatability and fairness in our evaluation, we designed and built a conducted wireless evaluation platform which provides a controlled test environment. Using our conducted test-bed, we investigated the performance of the different wireless mesh products in terms of their singlehop and multi-hop capacity under varying link conditions, and their ability to handle link failures. We have also conducted an outdoor multi-hop capacity test with the wireless mesh products, and compared the outdoor performance with the lab-based results. The test scenarios and the corresponding results demonstrate the flexibility and advantages of our conducted test-bed in fleshing out the performance differences of the evaluated mesh products. From our test results, we observed the differences in the MAC auto-rate behaviour of the different mesh network systems, as well as the throughput performance stability in one of the vendor's mesh routers. Our results also show that the multi-hop throughput performance of an unplanned (or rapid) network deployment can be substantially lower (ranging from 44% to 67%) compared to that of a planned network deployment.

Context-aware applications adapt to changing computing environments or changing user circumstances/tasks. Context information that supports such adaptations is provided by the underlying infrastructure, which gathers, pre-processes and provisions context information from a variety of context information sources. Such an infrastructure is prone to failures and disconnections that negatively impact on the ability of context-aware applications to adapt (and therefore dramatically impact on their usability). This paper describes a model-based autonomic context management system (ACoMS) that can dynamically configure and reconfigure its context information gathering and pre-processing functionality in order to provide fault tolerant provisioning of context information. The approach uses standards based descriptions of context information sources to increase openness, interoperability and scalability of context-aware systems.