INFOCOM 2024 论文列表

The concept of the Metaverse has garnered growing interest from both academic and industry circles. The decentralization of both the integrity and security of digital items has spurred the popularity of play-to-earn (P2E) games, where players are entitled to earn and own digital assets which they may trade for physical-world currencies. However, these computationally-intensive games are hardly playable on resource-limited mobile devices and the computational tasks have to be offloaded to an edge server. Through mobile edge computing (MEC), users can upload data to the Metaverse Service Provider (MSP) edge servers for computing. Nevertheless, there is a trade-off between user-perceived in-game latency and user visual experience. The downlink transmission of lower-resolution videos lowers user-perceived latency while lowering the visual fidelity and consequently, earnings of users. In this paper, we design a method to enhance the Metaverse-based mobile augmented reality (MAR) in-game user experience. Specifically, we formulate and solve a multi-objective optimization problem. Given the inherent NP-hardness of the problem, we present a low-complexity algorithm to address it, mitigating the trade-off between delay and earnings. The experiment results show that our method can effectively balance the user-perceived latency and profitability, thus improving the performance of Metaverse-based MAR systems.

There have been many studies leveraging bargaining to incentivize the sharing of network resources between resource owners and seekers. They predicted bargaining behavior and outcomes mainly by assuming that bargainers are fully rational and possess sufficient knowledge about their opponents. Our work addresses the prediction of bargaining behavior in network resource sharing scenarios where these assumptions do not hold, i.e., bargainers are bounded-rational and have heterogeneous knowledge. Our first key idea is using a multi-output Long Short-Term Memory (LSTM) neural network to learn bargainers’ behavior patterns and predict both their discrete and continuous decisions. Our second key idea is assigning a unique latent vector to each bargainer, characterizing the heterogeneity among bargainers. We propose a scheme to jointly learn the LSTM weights and latent vectors from real bargaining data, and utilize them to achieve a personalized behavior prediction. We prove that estimating our LSTM weights corresponds to a special design of LSTM training, and also theoretically characterize the performance of our scheme. To deal with large-scale datasets in practice, we further propose a variant of our scheme to accelerate the LSTM training. Experiments on a large real-world bargaining dataset demonstrate that our schemes achieve more accurate personalized predictions than baselines.

Reinforcement learning (RL)-based congestion control (CC) promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to human-derived, static CC algorithms. RL-based CC is in its early days and substantial research is required to understand existing limitations, identify research challenges and, eventually, yield deployable solutions for real-world networks. In this paper we present the first reproducible and systematic study of RL-based CC with the aim to highlight strengths and uncover fundamental limitations of the state-of-the-art. We identify challenges in evaluating RL-based CC, establish a methodology for studying said approaches and perform large-scale experimentation with RL-based CC approaches that are publicly available. We show that existing approaches can acquire all available bandwidth swiftly and are resistant to non-congestive loss, however, this is commonly at the cost of excessive packet loss in normal operation. We show that, as fairness is not embedded directly into reward functions, existing approaches exhibit unfairness in almost all tested network setups. Finally, we provide evidence that existing RL-based CC approaches under-perform when the available bandwidth and end-to-end latency dynamically change. Our experimentation codebase and datasets are publicly available with the aim to galvanise the community towards transparency and reproducibility, which have been recognised as crucial for researching and evaluating machine-generated policies.

The Open Radio Access Network (O-RAN)-compliant solutions lack crucial details to perform effective control loops at multiple time scales. In this vein, we propose ORANUS, an O-RAN-compliant mathematical framework to allocate radio resources to multiple ultra Reliable Low Latency Communication (uRLLC) services. In the near-RT control loop, ORANUS relies on a novel Stochastic Network Calculus (SNC)-based model to compute the amount of guaranteed radio resources for each uRLLC service. Unlike traditional approaches as queueing theory, the SNC-based model allows ORANUS to ensure the probability the packet transmission delay exceeds a budget, i.e., the violation probability, is below a target tolerance. ORANUS also utilizes an RT control loop to monitor service transmission queues, dynamically adjusting the guaranteed radio resources based on detected traffic anomalies. To the best of our knowledge, ORANUS is the first O-RAN-compliant solution which benefits from SNC to carry out near-RT and RT control loops. Simulation results show that ORANUS significantly improves over reference solutions, with an average violation probability 10× lower.

While providing machine learning model as a service to process users’ inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients’ limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients’ inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL’s global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients’ decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%.

Website fingerprinting (WF) attack is a type of traffic analysis attack. It enables a local and passive eavesdropper situated between the Tor client and the Tor entry node to deduce which websites the client is visiting. Currently, deep learning (DL) based WF attacks have overcome a number of proposed WF defenses, demonstrating superior performance compared to traditional machine learning (ML) based WF attacks. To mitigate this threat, we present WFGuard, a fuzzing-testing-based traffic morphing WF defense technique. WFGuard employs fine-grained neuron information within WF classifiers to design a joint optimization function and then applies gradient ascent to maximize both neurons value and misclassification possibility in DL-based WF classifiers. During each traffic mutation cycle, we propose a gradient based dummy traffic injection pattern generation approach, continuously mutating the traffic until a pattern emerges that can successfully deceive the classifier. Finally, the pattern present in successful variant traces are extracted and applied as defense strategies to Tor traffic. Extensive evaluations reveal that WFGuard can effectively decrease the accuracy of DL-based WF classifiers (e.g., DF and Var-CNN) to a mere 4.43%, while only incurring an 11.04% bandwidth overhead. This highlights the potential efficacy of our approach in mitigating WF attacks.

Despite the proven capabilities of deep neural networks (DNNs) for radio frequency (RF) fingerprinting, their security vulnerabilities have been largely overlooked. Unlike the extensively studied image domain, few works have explored the threat of backdoor attacks on RF signals. In this paper, we analyze the susceptibility of DNN-based RF fingerprinting to backdoor attacks, focusing on a more practical scenario where attackers lack access to control model gradients and training processes. We propose leveraging explainable machine learning techniques and autoencoders to guide the selection of positions and values, enabling the creation of effective backdoor triggers in a model-agnostic manner. To comprehensively evaluate our backdoor attack, we employ four diverse datasets with two protocols (Wi-Fi and LoRa) across various DNN architectures. Given that RF signals are often transformed into the frequency or time-frequency domains, this study also assesses attack efficacy in the time-frequency domain. Furthermore, we experiment with potential defenses, demonstrating the difficulty of fully safeguarding against our attacks.

Ambient LTE backscatter is a promising way to enable ubiquitous wireless communication with ultra-low power and cost. However, modulation in previous LTE backscatter systems relies heavily on the original data (content) of the signals. They either demodulate tag data using an additional receiver to provide the content of the excitation or modulate on a few predefined reference signals in random ambient LTE traffic.This paper presents CABLTE, a content-agnostic backscatter system that efficiently utilizes uncontrolled LTE PHY resources for backscatter communication using a single receiver. Our system is superior to prior work in two aspects: 1) Using one receiver to obtain tag data makes CABLTE more practical in real-world applications, and 2) Efficient modulation on LTE PYH resources improves the data rate of backscatter communication. To obtain the tag data without knowing the ambient content, we design a checksum-based codeword translation method. We also propose a customized channel estimation scheme and a signal identification component in the backscatter system to ensure our accurate modulation and demodulation. Extensive experiments show that our CABLTE provides maximum tag throughput of 22 kbps, which is 3.67x higher than the content-agnostic system CAB and even 1.38x higher than the content-based system SyncLTE.

Learning the principal eigenfunctions of a kernel is at the core of many machine-learning problems. Common methods usually deal with symmetric kernels based on Mercer’s Theorem. However, in the communication systems, the channel kernel is usually asymmetric due to the inconsistencies between the uplink and the downlink propagation environment. In this paper, we propose an explainable Neural Network for extracting eigenfunctions from generic multi-dimensional asymmetric channel kernels based on a recent method called High Order Generalized Mercer’s Theorem (HOGMT), by decomposing it into jointly orthogonal eigenfunctions. The proposed neural network based approach is efficient and can be easily implemented compared to the conventional SVD based solutions used for eigen decomposition. We also discuss the effect of different hyperparameters on the training time, constraint satisfaction, and overall performance. Finally, we show that multiplexing using these eigenfunctions mitigates interference across all the available Degrees of Freedom (DoF), both mathematically as well as via neural network based system-level simulations.

Crowdsensing networks for the sole purpose of performing spectrum measurements have resulted in prior initiatives that have failed primarily due to their costs for maintenance. In this paper, we take a different view and propose ORAN-Sense, a novel architecture of Internet of Things (IoT) spectrum crowd-sensing devices integrated into the Next Generation of cellular networks. We use this framework to extend the capabilities of 5G networks and localize a transmitter that does not collaborate in the process of positioning. While 5G signals can not be applied to this scenario as the transmitter does not participate in the localization process through dedicated pilot symbols and data, we show how to use Time Difference of Arrival-based positioning using low-cost spectrum sensors, minimizing hardware impairments of low-cost spectrum receivers, introducing methods to address errors caused by over-the-air signal propagation, and proposing a low-cost synchronization technique. We have deployed our localization network in two major cities in Europe. Our experimental results indicate that signal localization of non-collaborative transmitters is feasible even using low-cost radio receivers with median accuracies of tens of meters with just a few sensors spanning cities, which makes it suitable for its integration in the Next Generation of cellular networks.

While the fast adoption of RDMA in data centers has been primarily driven by its performance benefits, more and more attention is being paid to its security implication, especially with mounting security risks associated with lateral communication within data centers. However, since RDMA is implemented as NIC’s fixed function, it is challenging to incorporate any new security feature in RDMA. In this paper, we propose Zeta, a zero-trust security addon for RoCEv2, which enables network-independent, fine-grained zero-trust security control for RDMA. It does not require any change in RDMA’s ASIC implementation or application-level interfaces. To this end, Zeta leverages modern SmartNIC’s versatility to perform zero-trust policy control on RDMA packets within a SmartNIC in a cryptographically secure fashion. From its prototype implementation and evaluation based on real-word applications, we show that, while cryptographic verification of Zeta introduces 1.5 ms session startup latency, the overhead of end-to-end application performance is marginal (e.g., less than 1% throughput and 5% latency penalty).

We consider the scenario where an energy harvesting source sends its updates to a receiver. The source optimizes its energy allocation over a decision period to maximize a sum of time-varying functions of the age of information (AoI), representing the value of providing timely information. In a practical online setting, we need to make irrevocable energy allocation decisions at each time while the time-varying functions and the energy arrivals are only revealed sequentially. The problem is then challenging as 1) we are facing uncertain energy harvesting arrivals and time-varying functions, and 2) the energy allocation decisions and the energy harvesting process are coupled due to the capacity-limited battery. In this paper, we develop an optimal online algorithm CR-Reserve and show it achieves (lnθ + 1)-competitive, where θ is a parameter representing the level of uncertainty of the time-varying functions. It is the optimal competitive ratio among all deterministic and randomized online algorithms. We conduct simulations based on real-world traces and compare our algorithms with conceivable alternatives. The results show that our algorithms achieve 12% performance improvement as compared to the state-of-the-art baseline.

As edge computing capabilities increase, model learning deployments in diverse edge environments have emerged. In experimental design networks, introduced recently, network routing and rate allocation are designed to aid the transfer of data from sensors to heterogeneous learners. We design efficient experimental design network algorithms that are (a) distributed and (b) use multicast transmissions. This setting poses significant challenges as classic decentralization approaches often operate on (strictly) concave objectives under differentiable constraints. In contrast, the problem we study here has a non-convex, continuous DR-submodular objective, while multicast transmissions naturally result in non-differentiable constraints. From a technical standpoint, we propose a distributed Frank-Wolfe and a distributed projected gradient ascent algorithm that, coupled with a relaxation of non-differentiable constraints, yield allocations within a 1 − 1/e factor from the optimal. Numerical evaluations show that our proposed algorithms outperform competitors with respect to model learning quality.

Authenticating RFID-tagged items during mobile inventory, such as entering or leaving the warehouse, is a critical task for anti-counterfeiting. However, past authentication solutions using commercial off-the-shelf (COTS) devices cannot be applied in mobile scenarios, such as conveyors or tunnels, due to either high latency or non-robustness to tag movement. This paper introduces LoPrint, the first system to effectively authenticate mobile tagged items using the COTS orthogonal antennas existing in most infrastructures. The key insight of LoPrint is to randomly attach multiple tags on each item as a tag group and leverage the stable layout relationships of this tag group as novel fingerprints, including the relative distance matrix (RDM) and relative orientation matrix (ROM). Additionally, a new hardware fingerprint called cross-polarization ratio (CPR) is proposed to help distinguish the tag category. Furthermore, a lightweight approach is designed to robustly extract RDM, ROM, and CPR from RSSI and phase sequences under various environmental factors. LoPrint is prototyped and deployed on a conveyor in a lab environment and a tunnel in a real-world RFID warehouse, where 726 tagged items with random layouts are used for evaluation. Experimental results show that LoPrint can achieve a high authentication accuracy of 82.92% on the fixed conveyor and 79.48% on the random warehouse trolley when the size of tag group is three, outperforming the transferred stateof-the-art solution by over 10×.

The development of the Industrial Internet of Things (IIoT) is impeded by the lack of unknown protocol specifications. Protocol Reverse Engineering (PRE) plays a crucial role in inferring unpublished protocol specifications by analyzing traffic messages. Since different types within a protocol often have distinct formats, inferring the protocol type is essential for subsequent reverse analysis. Natural Language Processing (NLP) models have demonstrated remarkable capabilities in various sequence tasks, and traffic messages of unknown protocols can be analyzed as sequences. In this paper, we propose a framework for clustering unknown industrial control protocol types. Our framework utilizes a transformer-based auto-encoder network to train corresponding request and response messages, leveraging intermediate layer embedding vectors learned by the network for clustering. The clustering results are employed to extract candidate keywords and establish empirical rules. Subsequently, rule-based re-clustering is performed, and its effectiveness is evaluated based on previous clustering results. Through this re-clustering process, we identify the most effective combination of keywords that define the type. We evaluate the proposed framework using three general protocols that have different type rules and successfully separate the protocol internal types completely.

This research examines quantized uplink multi-user MIMO communication systems with low-resolution quantizers at users and base stations (BS). In such a system, we employ the non-orthogonal multiple access (NOMA) technique for communication between users and the BS to enhance communication performance. To maximize the number of users that satisfy the quality of service (QoS) requirement while minimizing the user’s transmit power, we jointly optimize the transmit power and precoding matrices at the users and the digital beamforming matrix at the BS. Owing to the non-convexity of the objective function, we transform the problem into a reinforcement learning-based problem and propose a deep reinforcement learning (DRL) framework named QNOMA-DRLPA to overcome the challenge. Because the nature of the action decided by the DRL algorithm may not satisfy the problem constraints, we propose a postactor process to redesign the actions to meet all the problem constraints. In the simulation, we assess the proposed framework’s performance in training convergence and demonstrate its superior performance under various environmental parameters compared with other benchmark schemes.

This paper introduces a novel paradigm for learning-based RF sensing, termed Pre-training RF signals In Sparsity-aware Masked autoencoders (PRISM), which shifts the RF sensing paradigm from supervised training on limited annotated datasets to unsupervised pre-training on large-scale unannotated datasets, followed by fine-tuning with a small annotated dataset. PRISM leverages a carefully designed sparsity-aware masking strategy to predict missing contents by masking a portion of RF signals, resulting in an efficient pre-training framework that significantly reduces computation and memory resources. This addresses the major challenges posed by large-scale and high-dimensional RF datasets, where memory consumption and computation speed are critical factors. We demonstrate PRISM’s excellent generalization performance across diverse RF sensing tasks by evaluating it on three typical scenarios: human silhouette segmentation, 3D pose estimation, and gesture recognition, involving two general RF devices, radar and WiFi. The experimental results provide strong evidence for the effectiveness of PRISM as a robust learning-based solution for large-scale RF sensing applications.

In social media platforms such as Weibo, Twitter, and Facebook, a variety of information is diffused daily. Exploring and exploiting the diffusion patterns in this information play crucial roles in areas such as viral marketing, recommendation systems, and public opinion management. However, the diffusion of this information is not merely sequential propagation among users, as most researchers assume. When we observe the diffusion of information in the entire network from a macroscopic perspective, we discover that these phenomena of information diffusion exhibit a series of interconnected relationships, such as alternation or dependency. In traditional methods of information diffusion prediction (IDP), these aspects are often overlooked. To address this, we introduce a substitution theory of information diffusion, minimal substitution (MS), and we combine it with neural networks to design a network model known as MSNN. First, the incorporation of MS theory enables our model to effectively capture the complex interrelations among pieces of information. Second, we analyze the relationship of the multi-scale IDP task, develop a one-step MS-based microscopic IDP method and a dynamic MS-based macroscopic IDP method, and utilize these two methods for joint training to achieve multi-scale prediction. Finally, we validate the accuracy of the proposed MSNN model through training on two real-world datasets with different growth patterns.

Age of information (AoI) is a crucial metric in modern communication systems, quantifying the information freshness at the receiver side. This study proposes a novel and general approach utilizing stochastic hybrid systems (SHS) for AoI analysis and minimization in carrier sense multiple access (CSMA) networks. Specifically, we consider a practical networking scenario where multiple nodes contend for transmission through a standard CSMA-based medium access control (MAC) protocol, and the tagged node under consideration uses a small transmission buffer for a low AoI. We for the first time develop an SHS-based analytical model for this finite-buffer transmission system over the CSMA MAC. Moreover, we develop a creative method to incorporate the collision probability into the SHS model, with background nodes having heterogeneous traffic arrival rates. This new model enables us to analytically find the optimal sampling rate to minimize the AoI of the tagged node in a wide range of practical networking scenarios. Our analysis reveals insights into buffer size impacts when jointly optimizing throughput and AoI. The SHS model is cast over an 802.11-based MAC to examine the performance, with comparison to ns-based simulation results. The accuracy of the modeling and the efficiency of optimal sampling are convincingly demonstrated.