INFOCOM 2024 论文列表

Payment Channel Networks (PCNs) have been proposed as a second-layer solution to the scalability issue of blockchain-based cryptocurrencies, most developed systems still lack effective strategies for further scalability solutions. Virtual payment channel (VPC) has been proposed as an off-chain technique that avoids the involvement of intermediaries for payments in a PCN. However, there is no research on how to efficiently construct VPCs while considering the characteristics of the underlying PCN. To fill this void, this paper focuses on the VPC construction in a PCN. More specifically, we propose a metric, Capacity to the Number of Intermediaries Ratio (CNIR), to consider both the capacity of the constructed VPC and the collateral locked by the involved users. We first study the VPC construction problem for a single pair of users and design an efficient algorithm that achieves the optimal CNIR. Based on this, we propose Thor, a protocol that constructs a virtual payment channel network (VPCN) for multiple pairs. Evaluation results show that Thor can efficiently construct a VPCN and outperform baseline algorithms in terms of the CNIR.

Computation offloading is one of the key issues in mobile edge computing (MEC) that alleviates the tension between user equipment's limited capabilities and mobile application's high requirements. To achieve model-free computation offloading when reliable MEC dynamics are unavailable, deep reinforcement learning (DRL) has become a popular methodology. However, most existing DRL-based offloading approaches are developed for a single MEC environment, with invariant system bandwidth, edge capability, task types, etc., while realistic MEC scenarios tend to be of high diversity. Unfortunately, in multi-MEC environments, DRL-based offloading faces at least two challenges, learning inefficiency and interference of offloading experiences. To address the challenges, we propose a DRL-based Multi-environmental Module-compositional Modelfree computation OFFloading (M3OFF) framework. M3OFF generates offloading policies using module composition instead of a single DRL network so that learning efficiency could be improved by reusing the same modules and learning interference could be reduced by composing different modules. Furthermore, we design multiple module composition-specific training methods for M3OFF, including alternate modules-and-composer updates to improve training stability, loss-regularization to avoid module degeneration, and module-dropout to mitigate overfitting. Extensive experimental results on both simulation and testbed demonstrate that M3OFF outperforms the performances of most state-of-the-arts in multi-MEC and reaches close to single-MEC.

Backscatter sensing has shown great potential in the Internet of Things (IoT) and has attracted substantial research interest. We present LoMu, the first long-range multi-target backscatter sensing system for low-cost tags under ambient LoRa. LoMu analyzes the received low-SNR backscatter signals from different tags and calculates their phases to derive the motion information. The design of LoMu faces practical challenges including near-far interference between multiple tags, phase offsets induced by unsynchronized transceivers, and phase errors due to frequency drift in low-cost tags. We propose a conjugate-based energy concentration method to extract high-quality signals and a Hamming-window-based method to alleviate the near-far problem. We then leverage the relationship between the excitation signal and backscatter signals to synchronize TX and RX. Finally, we combine the double sidebands of backscatter signals to cancel the tag frequency drift. We implement LoMu and conduct extensive experiments to evaluate its performance. The results demonstrate that LoMu can accurately sense 35 tags at the same time. The average frequency sensing error is 0.7% at 400m, which is 4× distance of the state-of-the-art.

Traffic measurement provides essential information for various network services. Burst is a common phenomenon in high-speed network streams, which manifests as a surge in the number of incoming packets in a flow. We propose a new definition named across-period burst, considering the change not in two adjacent time windows but in two groups of windows with time continuity. The across-period burst definition can better capture the continuous changes of flows in high-speed networks. To achieve real-time burst detection with high accuracy and low memory consumption, we propose a novel sketch named BurstDetector, which consists of two stages. Stage 1 excludes those flows that will not become burst flows, while Stage 2 accurately records the information of the potential burst flows and carries out across-period burst detections at the end of every time window. We further propose an optimization called Hierarchical Cell, which can improve the memory utilization of BurstDetector. In addition, we analyze the estimation accuracy and time complexity of BurstDetector. Extensive experiments based on real-world datasets show that our BurstDetector can achieve at least 2.8 times as much detection accuracy and processing throughput as some existing algorithms.

Federated learning (FL) encounters scalability challenges when implemented over fog networks. Semi-decentralized FL (SD-FL) proposes a solution that divides model cooperation into two stages: at the lower stage, device-to-device (D2D) communications is employed for local model aggregations within subnetworks (subnets), while the upper stage handles device-server (DS) communications for global model aggregations. However, existing SD-FL schemes are based on gradient diversity assumptions that become performance bottlenecks as data distributions become more heterogeneous. In this work, we develop semi-decentralized gradient tracking (SD-GT), the first SD-FL methodology that removes the need for such assumptions by incorporating tracking terms into device updates for each communication layer. Analytical characterization of SD-GT reveals convergence upper bounds for both non-convex and strongly-convex problems, for a suitable choice of step size. We employ the resulting bounds in the development of a co-optimization algorithm for optimizing subnet sampling rates and D2D rounds according to a performance-efficiency trade-off. Our subsequent numerical evaluations demonstrate that SD-GT obtains substantial improvements in trained model quality and communication cost relative to baselines in SD-FL and gradient tracking on several datasets.

Malicious entities abuse advanced modulation classification (MC) techniques to launch traffic analysis, selective jamming, evasion, and poison attacks. Recent studies show that current defenses against such attacks are static in nature and vulnerable to persistent adversaries who invest time and resources into learning the defenses, thereby being able to design and execute more sophisticated attacks to circumvent them. In this paper, we present a moving-target defense framework to support a novel modulation-masking mechanism we develop against advanced and persistent MC attacks. The modulated symbols are first masked using small perturbations to make them appear to an adversary in a state of ambiguity about the model as if they are from another modulation scheme. By deploying a pool of deep learning models and perturbation-generating techniques, our defense strategy keeps changing (moving) them as needed, making it difficult (cubic time complexity) for adversaries to keep up with the evolving defense system over time. We show that the overall system performance remains unaffected under our technique. We further demonstrate that, over time, a persistent adversary can learn and eventually circumvent our masking technique, along with other existing defenses, unless a moving target defense approach is adopted.

Spectrum has become an extremely scarce and congested resource. As a consequence, spectrum sensing enables the coexistence of different wireless technologies in shared spectrum bands. Most existing work requires spectrograms to classify signals. Ultimately, this implies that images need to be continuously created from I/Q samples, thus creating unacceptable latency for real-time operations. In addition, spectrogram-based approaches do not achieve sufficient granularity level as they are based on object detection performed on pixels and are based on rectangular bounding boxes. For this reason, we propose a completely novel approach based on semantic spectrum segmentation, where multiple signals are simultaneously classified and localized in both time and frequency at the I/Q level. Conversely from the state-of-the-art computer vision algorithm, we add non-local blocks to combine the spatial features of signals, and thus achieve better performance. In addition, we propose a novel data generation approach where a limited set of easy-to-collect real-world wireless signals are "stitched together" to generate large-scale, wideband, and diverse datasets. Experimental results obtained on multiple testbeds (including the Arena testbed) using multiple antennas, multiple sampling frequencies, and multiple radios over the course of 3 days show that our approach classifies and localizes signals with a mean intersection over union (IOU) of 96.70% across 5 wireless protocols while performing in real-time with a latency of 2.6 ms. Moreover, we demonstrate that our approach based on non-local blocks achieves 7% more accuracy when segmenting the most challenging signals with respect to the state-of-the-art U-Net algorithm. We will release our 17 GB dataset and code.

Edge computing gained popularity for its promises of low latency and high-quality computing services to users. However, it has also introduced the challenge of mutual untrust between user and edge devices for service level agreement (SLA) compliance. This obstacle hampers wide adoption of edge computing, especially in pervasive edge computing (PEC) where edge devices can freely enter or exit the market, which makes verifying and enforcing SLAs significantly more challenging. In this paper, we propose a framework for verifying and enforcing SLAs in PEC, allowing a user to assess SLA compliance of an edge service and ensure correctness of the service results. Our solution, called VeriEdge, employs a verifiable delayed sampling approach to sample a small number of computation steps, and relies on randomly selected verifiers to verify correctness of the computation results. To make sure the verification process is non-manipulable, we employ verifiable random functions to post-select the verifier(s). A dispute protocol is designed to resolve disputes for potential misbehavior. Rigorous security analysis demonstrates that VeriEdge achieves a high probability of detecting SLA violation with a minimal overhead. Experimental results indicate that VeriEdge is lightweight, practical, and efficient.

The emerging high-capacity optical networks makes it urgent to design large-scale flexible mesh optical cross-connects (OXCs). Though Clos network is the theory for building scalable and cost-effective switching fabrics, the nonblocking conditions of flex-grid optical Clos networks without wavelength conversion remain unknown. This paper studies the nonblocking conditions for the flex-grid OXC-Clos network, which is constructed from a number of small-size standard OXCs. We first show that a strictly nonblocking (SNB) OXC-Clos network will incur a high cost, as small-granularity lightpaths may abuse central modules, rendering them unavailable for large-granularity requests due to frequency conflicts. We thus propose a granularity differential routing (GDR) strategy, the idea of which is to restrict the set of CMs that can be used by the lightpaths of each granularity. Under the GDR strategy, we investigate two system models, granularity-port binding and unbinding models, and prove the wide-sense nonblocking (WSNB) conditions for OXC-Clos network. We show that the cost of WSNB network is remarkably smaller than that of SNB network, and find that the second model can lead to more flexible network-bandwidth utilization than the first model only at a small cost of switching fabrics.

In this paper, we propose a cross-domain, scalable, and interpretable radio frequency (RF) fingerprinting system using a modified prototypical network (PTN) and an explanation-guided data augmentation across various domains and datasets with only a few samples. Specifically, a convolutional neural network is employed as the feature extractor of the PTN to extract RF fingerprint features. The predictions are made by comparing the similarity between prototypes and feature embedding vectors. To further improve the system performance, we design a customized loss function and deploy an eXplainable Artificial Intelligence (XAI) method to guide data augmentation during fine-tuning. To evaluate the effectiveness of our system in addressing domain shift and scalability problems, we conducted extensive experiments in both cross-domain and novel-device scenarios. Our study shows that our approach achieves exceptional performance in the cross-domain case, exhibiting an accuracy improvement of approximately 80% compared to convolutional neural networks in the best case. Furthermore, our approach demonstrates promising results in the novel-device case across different datasets. Our customized loss function and XAI-guided data augmentation can further improve authentication accuracy to a certain degree.

Survivable routing is crucial in backbone networks to ensure connectivity, even during failures. At network design, groups of network elements prone to potential failure events are identified. These groups are referred to as Shared Risk Link Groups (SRLGs), and if they are a set of links intersected by a connected region of the plane, we call them regional-SRLGs. A recent study has presented a polynomial-time algorithm for finding a maximum number of regional-SRLG-disjoint paths between two given nodes in a planar topology, with the paths being nodedisjoint. However, existing algorithms for this problem are not practical due to their runtime and implementation complexities.This paper investigates a more general model, the maximum number of non-crossing, regional-SRLG-disjoint paths problem. It introduces an efficient and easily implementable algorithmic framework, leveraging an arbitrarily chosen shortest path finding subroutine for graphs with possibly negative weights. Depending on the subroutine chosen, the framework improves the previous worst-case runtime complexity, or can solve the problem w.h.p. in near-linear expected time. The proposed framework enables the first additive approximation for a more general ${\mathcal{N}}{\mathcal{P}}$ -hard version of the problem, where the objective is to find the maximum number of regional-SRLG-disjoint paths. We validate our findings through extensive simulations.

Holographic Metasurface Transceivers (HMTs) are emerging as cost-effective substitutes to large antenna arrays for beamforming in Millimeter and TeraHertz wave communication. However, to achieve desired channel gains through beamforming in HMT, phase-shifts of a large number of elements need to be appropriately set, which is challenging. Also, these optimal phase-shifts depend on the location of the receivers, which could be unknown. In this work, we develop a learning algorithm using a fixed-budget multi-armed bandit framework to beamform and maximize received signal strength at the receiver for far-field regions. Our algorithm, named Holographic Beam (HoloBeam) exploits the parametric form of channel gains of the beams, which can be expressed in terms of two phase-shifting parameters. Even after parameterization, the problem is still challenging as phase-shifting parameters take continuous values. To overcome this, HoloBeam works with the discrete values of phase-shifting parameters and exploits their unimodal relations with channel gains to learn the optimal values faster. We upper bound the probability of HoloBeam incorrectly identifying the (discrete) optimal phase-shift parameters in terms of the number of pilots used in learning. We show that this probability decays exponentially with the number of pilot signals. We demonstrate that HoloBeam outperforms state-of-the-art algorithms through extensive simulations.

Industrial protocols are widely used in Industrial Control Systems (ICSs) to network physical devices, thus playing a crucial role in securing ICSs. However, most commercial industrial protocols are proprietary and owned by their vendors, which impedes the implementation of protections against cyber threats. In this paper, we design REInPro to Reverse Engineer Industrial Protocols. REInPro is inspired by the fact that the structure of industrial protocols can be determined by a particular field referred to control field. By applying a probabilistic model of network traffic behavior, REInPro automatically identifies the control field and groups the associated network traffic into clusters. REInPro then infers critical semantics of industrial protocols by differentiating the features of corresponding protocol fields. We have experimentally implemented and evaluated REInPro using 8 different industrial protocols across 6 Programmable Logic Controllers (PLCs) belonging to 5 original equipment manufacturers. The experimental results show REInPro to reverse-engineer the formats and semantics of industrial protocols with an average correctness/perfection of 0.70/0.58 and 0.96/0.39.

The collaboration between clouds and edges unlocks the full potential of edge-cloud systems. Edge-cloud platform has brought about significant decentralization, heterogeneity, complexity, and instability. These characteristics have posed unprecedented challenges to the optimal scheduling problem in the edge-cloud system, including inaccurate decision-making and slow convergence. In this paper, we propose a curiosity-driven collaborative request scheduling scheme in edge-cloud systems, namely Cur-CoEdge. To tackle the challenge of inaccurate decision-making, we introduce a time-scale and decision-level interaction mechanism. This mechanism employs a small-large-time-scale scheduling learning framework, facilitating mutual learning between different decision levels. To address the challenge of slow convergence, we investigate the underlying reasons, such as the sparse reward-setting in reinforcement learning. In response, we develop a curiosity-driven collaborative exploration approach that fosters intrinsic curiosity in the cloud and simultaneously motivates dispatchers to explore the environment both individually and collectively. The effectiveness of this collaborative exploration is also supported by theoretical proof of convergence. Finally, we implement a prototype system on a network hardware system along with two real-world traces. Evaluations demonstrate significant improvements, with up to a 26% increase in time efficiency, a 40% rise in system throughput, and a 71% enhancement in convergence speed.

P4 is widely adopted for programming data planes in software-defined networking. Formal verification of P4 programs is essential to ensure network reliability and security. However, existing P4 verifiers overlook the stateful nature of packet processing, rendering them inadequate for verifying complex stateful P4 programs.In this paper, we introduce a novel concept called packet invariants to address the stateful aspects of P4 programs. We present an automated verification tool specifically designed for stateful P4 programs. This algorithm efficiently discovers and validates packet invariants in a data-driven manner, offering a novel and effective verification approach for stateful P4 programs. To the best of our knowledge, this approach represents the first attempt to generate and leverage domain-specific invariants for P4 program verification. We implement our approach in a prototype tool called P4Inv. Experimental results demonstrate its effectiveness in verifying stateful P4 programs.

Time-Sensitive Networking (TSN) is an enabling technology for Industry 4.0. Traffic scheduling plays a key role for TSN to ensure low-latency and deterministic transmission of critical traffic. As industrial network scales, TSN networks are expected to support a rising number of both time-triggered and event-triggered critical traffic (TCT and ECT). In this work, we present InNetScheduler, the first in-network TSN scheduling paradigm that boosts the throughput, i.e., number of scheduled data flows, of both traffic types. Different from existing approaches that conduct entire scheduling on the server, InNetScheduler leverages the computation resources on switches to promptly schedule latency-critical ECT, and delegate the computational-intensive TCT scheduling to server. The key innovation of InNetScheduler includes a Load-Aware Optimizer to mitigate ECT conflicts, a Relaxated ECT Scheduler to accelerate in-network computation, and End-to-End Determinism Guarantee to lower scheduling jitter. We fully implement a suite of InNetScheduler-compatible TSN switches with hardwaresoftware co-design. Extensive experiments are conducted on both simulation and physical testbeds, and the results demonstrate InNetScheduler’s superior performance. By unleashing the power of in-network computation, InNetScheduler points out a direction to extend the capacity of existing industrial networks.

Camera sensors have been widely used to perceive the vehicle surrounding environments, understand the traffic condition, and then help avoid traffic accidents. Since most sensors are limited by line of sight, the perception data collected through individual vehicle can be uploaded and shared through the edge server. To reduce the bandwidth, storage and processing cost, we propose an edge-assisted camera selection system that only selects the necessary camera images to upload to the server. The selection is based on the camera metadata which describes the coverage of the cameras represented with GPS locations, orientations, and field of views. Different from existing work, our metadata based approach can detect and locate camera occlusions by leveraging LiDAR sensors, and then precisely and quickly calculate the real camera coverage and identify the coverage overlap. Based on the camera metadata, we study two camera selection problems, the Max-Coverage problem and the Min-Selection problem, and solve them with efficient algorithms. Moreover, we propose similarity based redundancy suppression techniques to further reduce the bandwidth consumption which becomes significant due to vehicle movements. Extensive evaluations demonstrate that the proposed algorithms can effectively select cameras to maximize coverage or minimize bandwidth consumption based on the application requirements.

Datacenter applications increasingly demand microsecond-scale latency and tight tail latency. Despite recent advances in datacenter transport protocols, we notice that the timeout caused by packet loss is the killer of microsecond-scale latency. Moreover, refining the RTO setting is impractical due to the significant fluctuations in RTT. In this paper, we propose explicit dropping notification (EDN) to avoid timeouts. EDN rekindles ICMP Source Quench, where the switch notifies the source of precise packet loss information. Then the source can rapidly pinpoint dropped packets for fast retransmission instead of waiting for timeouts. More importantly, fast retransmission does not mean immediate retransmission which is prone to aggravate congestion and deteriorate latency. In light of this, we suggest finessing the timing and sending rate of retransmission. Specifically, as a reward of the paradigm shift to explicit notification, the source can pause for the queue draining time piggybacked on EDN messages and estimate connection capacity to figure out a proper sending rate, thus avoiding congestion aggravation. We implement EDN on the P4-programmable switching ASIC and Linux kernel. Evaluations show that, compared with state-of-the-art loss recovery schemes, EDN reduces the latency by up to 4.1× on average and 3.6× at the 99th-percentile.

DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs). The motivation for designing DTMM comes from the emerging field of tiny machine learning (TinyML), which explores extending the reach of machine learning to many low-end IoT devices to achieve ubiquitous intelligence. Due to the weak capability of embedded devices, it is necessary to compress models by pruning enough weights before deploying. Although pruning has been studied extensively on many computing platforms, two key issues with pruning methods are exacerbated on MCUs: models need to be deeply compressed without significantly compromising accuracy, and they should perform efficiently after pruning. Current solutions only achieve one of these objectives, but not both. In this paper, we find that pruned models have great potential for efficient deployment and execution on MCUs. Therefore, we propose DTMM with pruning unit selection, pre-execution pruning optimizations, runtime acceleration, and post-execution low-cost storage to fill the gap for efficient deployment and execution of pruned models. It can be integrated into commercial ML frameworks for practical deployment, and a prototype system has been developed. Extensive experiments on various models show promising gains compared to state-of-the-art methods.