arXiv subjects

Xiuzhen Cheng

Publications and source records attributed to Xiuzhen Cheng.

At least 73 records · Page 4Linked to original sources

arXiv2023

Spatial Crowdsourcing Task Allocation Scheme for Massive Data with Spatial Heterogeneity

Spatial crowdsourcing (SC) engages large worker pools for location-based tasks, attracting growing research interest. However, prior SC task allocation approaches exhibit limitations in computational efficiency, balanced matching, and participation incentives. To address these challenges, we propose a graph-based allocation framework optimized for massive heterogeneous spatial data. The framework first clusters similar tasks and workers separately to reduce allocation scale. Next, it constructs novel non-crossing graph structures to model balanced adjacencies between unevenly distributed tasks and workers. Based on the graphs, a bidirectional worker-task matching scheme is designed to produce allocations optimized for mutual interests. Extensive experiments on real-world datasets analyze the performance under various parameter settings.

cs.DC↗

arXiv2023

An Adaptive and Modular Blockchain Enabled Architecture for a Decentralized Metaverse

A metaverse breaks the boundaries of time and space between people, realizing a more realistic virtual experience, improving work efficiency, and creating a new business model. Blockchain, as one of the key supporting technologies for a metaverse design, provides a trusted interactive environment. However, the rich and varied scenes of a metaverse have led to excessive consumption of on-chain resources, raising the threshold for ordinary users to join, thereby losing the human-centered design. Therefore, we propose an adaptive and modular blockchain-enabled architecture for a decentralized metaverse to address these issues. The solution includes an adaptive consensus/ledger protocol based on a modular blockchain, which can effectively adapt to the ever-changing scenarios of the metaverse, reduce resource consumption, and provide a secure and reliable interactive environment. In addition, we propose the concept of Non-Fungible Resource (NFR) to virtualize idle resources. Users can establish a temporary trusted environment and rent others' NFR to meet their computing needs. Finally, we simulate and test our solution based on XuperChain, and the experimental results prove the feasibility of our design.

cs.CR↗

arXiv2023

Collaborative Learning in General Graphs with Limited Memorization: Complexity, Learnability, and Reliability

We consider a K-armed bandit problem in general graphs where agents are arbitrarily connected and each of them has limited memorizing capabilities and communication bandwidth. The goal is to let each of the agents eventually learn the best arm. It is assumed in these studies that the communication graph should be complete or well-structured, whereas such an assumption is not always valid in practice. Furthermore, limited memorization and communication bandwidth also restrict the collaborations of the agents, since the agents memorize and communicate very few experiences. Additionally, an agent may be corrupted to share falsified experiences to its peers, while the resource limit in terms of memorization and communication may considerably restrict the reliability of the learning process. To address the above issues, we propose a three-staged collaborative learning algorithm. In each step, the agents share their latest experiences with each other through light-weight random walks in a general communication graph, and then make decisions on which arms to pull according to the recommendations received from their peers. The agents finally update their adoptions (i.e., preferences to the arms) based on the reward obtained by pulling the arms. Our theoretical analysis shows that, when there are a sufficient number of agents participating in the collaborative learning process, all the agents eventually learn the best arm with high probability, even with limited memorizing capabilities and light-weight communications. We also reveal in our theoretical analysis the upper bound on the number of corrupted agents our algorithm can tolerate. The efficacy of our proposed three-staged collaborative learning algorithm is finally verified by extensive experiments on both synthetic and real datasets.

cs.LG↗

arXiv2023

A Self-Correcting Sequential Recommender

Sequential recommendations aim to capture users' preferences from their historical interactions so as to predict the next item that they will interact with. Sequential recommendation methods usually assume that all items in a user's historical interactions reflect her/his preferences and transition patterns between items. However, real-world interaction data is imperfect in that (i) users might erroneously click on items, i.e., so-called misclicks on irrelevant items, and (ii) users might miss items, i.e., unexposed relevant items due to inaccurate recommendations. To tackle the two issues listed above, we propose STEAM, a Self-correcTing sEquentiAl recoMmender. STEAM first corrects an input item sequence by adjusting the misclicked and/or missed items. It then uses the corrected item sequence to train a recommender and make the next item prediction.We design an item-wise corrector that can adaptively select one type of operation for each item in the sequence. The operation types are 'keep', 'delete' and 'insert.' In order to train the item-wise corrector without requiring additional labeling, we design two self-supervised learning mechanisms: (i) deletion correction (i.e., deleting randomly inserted items), and (ii) insertion correction (i.e., predicting randomly deleted items). We integrate the corrector with the recommender by sharing the encoder and by training them jointly. We conduct extensive experiments on three real-world datasets and the experimental results demonstrate that STEAM outperforms state-of-the-art sequential recommendation baselines. Our in-depth analyses confirm that STEAM benefits from learning to correct the raw item sequences.

cs.IR↗

arXiv2023

Exploring Blockchain Technology through a Modular Lens: A Survey

Blockchain has attracted significant attention in recent years due to its potential to revolutionize various industries by providing trustlessness. To comprehensively examine blockchain systems, this article presents both a macro-level overview on the most popular blockchain systems, and a micro-level analysis on a general blockchain framework and its crucial components. The macro-level exploration provides a big picture on the endeavors made by blockchain professionals over the years to enhance the blockchain performance while the micro-level investigation details the blockchain building blocks for deep technology comprehension. More specifically, this article introduces a general modular blockchain analytic framework that decomposes a blockchain system into interacting modules and then examines the major modules to cover the essential blockchain components of network, consensus, and distributed ledger at the micro-level. The framework as well as the modular analysis jointly build a foundation for designing scalable, flexible, and application-adaptive blockchains that can meet diverse requirements. Additionally, this article explores popular technologies that can be integrated with blockchain to expand functionality and highlights major challenges. Such a study provides critical insights to overcome the obstacles in designing novel blockchain systems and facilitates the further development of blockchain as a digital infrastructure to service new applications.

cs.CR↗

arXiv2023

Byzantine-Resilient Federated Learning at Edge

Both Byzantine resilience and communication efficiency have attracted tremendous attention recently for their significance in edge federated learning. However, most existing algorithms may fail when dealing with real-world irregular data that behaves in a heavy-tailed manner. To address this issue, we study the stochastic convex and non-convex optimization problem for federated learning at edge and show how to handle heavy-tailed data while retaining the Byzantine resilience, communication efficiency and the optimal statistical error rates simultaneously. Specifically, we first present a Byzantine-resilient distributed gradient descent algorithm that can handle the heavy-tailed data and meanwhile converge under the standard assumptions. To reduce the communication overhead, we further propose another algorithm that incorporates gradient compression techniques to save communication costs during the learning process. Theoretical analysis shows that our algorithms achieve order-optimal statistical error rate in presence of Byzantine devices. Finally, we conduct extensive experiments on both synthetic and real-world datasets to verify the efficacy of our algorithms.

cs.DC↗

arXiv2023

Meta Matrix Factorization for Federated Rating Predictions

Federated recommender systems have distinct advantages in terms of privacy protection over traditional recommender systems that are centralized at a data center. However, previous work on federated recommender systems does not fully consider the limitations of storage, RAM, energy and communication bandwidth in a mobile environment. The scales of the models proposed are too large to be easily run on mobile devices. And existing federated recommender systems need to fine-tune recommendation models on each device, making it hard to effectively exploit collaborative filtering information among users/devices. Our goal in this paper is to design a novel federated learning framework for rating prediction (RP) for mobile environments. We introduce a federated matrix factorization (MF) framework, named meta matrix factorization (MetaMF). Given a user, we first obtain a collaborative vector by collecting useful information with a collaborative memory module. Then, we employ a meta recommender module to generate private item embeddings and a RP model based on the collaborative vector in the server. To address the challenge of generating a large number of high-dimensional item embeddings, we devise a rise-dimensional generation strategy that first generates a low-dimensional item embedding matrix and a rise-dimensional matrix, and then multiply them to obtain high-dimensional embeddings. We use the generated model to produce private RPs for the given user on her device. MetaMF shows a high capacity even with a small RP model, which can adapt to the limitations of a mobile environment. We conduct extensive experiments on four benchmark datasets to compare MetaMF with existing MF methods and find that MetaMF can achieve competitive performance. Moreover, we find MetaMF achieves higher RP performance over existing federated methods by better exploiting collaborative filtering among users/devices.

cs.IR↗

arXiv2023

Modeling Sequential Recommendation as Missing Information Imputation

Side information is being used extensively to improve the effectiveness of sequential recommendation models. It is said to help capture the transition patterns among items. Most previous work on sequential recommendation that uses side information models item IDs and side information separately, which may fail to fully model the relation between the items and their side information. Moreover, in real-world systems, not all values of item feature fields are available. This hurts the performance of models that rely on side information. Existing methods tend to neglect the context of missing item feature fields, and fill them with generic or special values, e.g., unknown, which might lead to sub-optimal performance. To address the limitation of sequential recommenders with side information, we define a way to fuse side information and alleviate the problem of missing side information by proposing a unified task, namely the missing information imputation (MII), which randomly masks some feature fields in a given sequence of items, including item IDs, and then forces a predictive model to recover them. By considering the next item as a missing feature field, sequential recommendation can be formulated as a special case of MII. We propose a sequential recommendation model, called missing information imputation recommender (MIIR), that builds on the idea of MII and simultaneously imputes missing item feature values and predicts the next item. We devise a dense fusion self-attention (DFSA) mechanism for MIIR to capture all pairwise relations between items and their side information. Empirical studies on three benchmark datasets demonstrate that MIIR, supervised by MII, achieves a significantly better sequential recommendation performance than state-of-the-art baselines.

cs.IR↗

arXiv2023

Meta Computing

With the continuous improvement of information infrastructures, academia and industry have been constantly exploring new computing paradigms to fully exploit computing powers. In this paper, we propose Meta Computing, a new computing paradigm that aims to utilize all available computing resources hooked on the Internet, provide efficient, fault-tolerant, and personalized services with strong security and privacy guarantee, and virtualize the Internet as a giant computer, that is, ``Network-as-a-Computer, NaaC'', or ``Meta Computer'' for short, for any task or any person on-demand.

cs.DC↗

arXiv2022

FileDAG: A Multi-Version Decentralized Storage Network Built on DAG-based Blockchain

Decentralized Storage Networks (DSNs) can gather storage resources from mutually untrusted providers and form worldwide decentralized file systems. Compared to traditional storage networks, DSNs are built on top of blockchains, which can incentivize service providers and ensure strong security. However, existing DSNs face two major challenges. First, deduplication can only be achieved at the directory-level. Missing file-level deduplication leads to unavoidable extra storage and bandwidth cost. Second, current DSNs realize file indexing by storing extra metadata while blockchain ledgers are not fully exploited. To overcome these problems, we propose FileDAG, a DSN built on DAG-based blockchain to support file-level deduplication in storing multi-versioned files. When updating files, we adopt an increment generation method to calculate and store only the increments instead of the entire updated files. Besides, we introduce a two-layer DAG-based blockchain ledger, by which FileDAG can provide flexible and storage-saving file indexing by directly using the blockchain database without incurring extra storage overhead. We implement FileDAG and evaluate its performance with extensive experiments. The results demonstrate that FileDAG outperforms the state-of-the-art industrial DSNs considering storage cost and latency.

cs.DC↗

arXiv2022

A Trustless Architecture of Blockchain-enabled Metaverse

Metaverse has rekindled human beings' desire to further break space-time barriers by fusing the virtual and real worlds. However, security and privacy threats hinder us from building a utopia. A metaverse embraces various techniques, while at the same time inheriting their pitfalls and thus exposing large attack surfaces. Blockchain, proposed in 2008, was regarded as a key building block of metaverses. it enables transparent and trusted computing environments using tamper-resistant decentralized ledgers. Currently, blockchain supports Decentralized Finance (DeFi) and Non-fungible Tokens (NFT) for metaverses. However, the power of a blockchain has not been sufficiently exploited. In this article, we propose a novel trustless architecture of blockchain-enabled metaverse, aiming to provide efficient resource integration and allocation by consolidating hardware and software components. To realize our design objectives, we provide an On-Demand Trusted Computing Environment (OTCE) technique based on local trust evaluation. Specifically, the architecture adopts a hypergraph to represent a metaverse, in which each hyperedge links a group of users with certain relationship. Then the trust level of each user group can be evaluated based on graph analytics techniques. Based on the trust value, each group can determine its security plan on demand, free from interference by irrelevant nodes. Besides, OTCEs enable large-scale and flexible application environments (sandboxes) while preserving a strong security guarantee.

cs.CR↗

arXiv2022

Cross-Channel: Scalable Off-Chain Channels Supporting Fair and Atomic Cross-Chain Operations

Cross-chain technology facilitates the interoperability among isolated blockchains on which users can freely communicate and transfer values. Existing cross-chain protocols suffer from the scalability problem when processing on-chain transactions. Off-chain channels, as a promising blockchain scaling technique, can enable micro-payment transactions without involving on-chain transaction settlement. However, existing channel schemes can only be applied to operations within a single blockchain, failing to support cross-chain services. Therefore in this paper, we propose Cross-Channel, the first off-chain channel to support cross-chain services. We introduce a novel hierarchical channel structure, a new hierarchical settlement protocol, and a smart general fair exchange protocol, to ensure scalability, fairness, and atomicity of cross-chain interactions. Besides, Cross-Channel provides strong security and practicality by avoiding high latency in asynchronous networks. Through a 50-instance deployment of Cross-Channel on AliCloud, we demonstrate that Cross-Channel is well-suited for processing cross-chain transactions in high-frequency and large-scale, and brings a significantly enhanced throughput with a small amount of gas and delay overhead.

cs.CR↗

arXiv2022

AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabulary

With the increasing popularity of voice-based applications, acoustic eavesdropping has become a serious threat to users' privacy. While on smartphones the access to microphones needs an explicit user permission, acoustic eavesdropping attacks can rely on motion sensors (such as accelerometer and gyroscope), which access is unrestricted. However, previous instances of such attacks can only recognize a limited set of pre-trained words or phrases. In this paper, we present AccEar, an accelerometerbased acoustic eavesdropping attack that can reconstruct any audio played on the smartphone's loudspeaker with unconstrained vocabulary. We show that an attacker can employ a conditional Generative Adversarial Network (cGAN) to reconstruct highfidelity audio from low-frequency accelerometer signals. The presented cGAN model learns to recreate high-frequency components of the user's voice from low-frequency accelerometer signals through spectrogram enhancement. We assess the feasibility and effectiveness of AccEar attack in a thorough set of experiments using audio from 16 public personalities. As shown by the results in both objective and subjective evaluations, AccEar successfully reconstructs user speeches from accelerometer signals in different scenarios including varying sampling rate, audio volume, device model, etc.

cs.SD↗

arXiv2022

Federated Learning Hyper-Parameter Tuning from a System Perspective

Federated learning (FL) is a distributed model training paradigm that preserves clients' data privacy. It has gained tremendous attention from both academia and industry. FL hyper-parameters (e.g., the number of selected clients and the number of training passes) significantly affect the training overhead in terms of computation time, transmission time, computation load, and transmission load. However, the current practice of manually selecting FL hyper-parameters imposes a heavy burden on FL practitioners because applications have different training preferences. In this paper, we propose FedTune, an automatic FL hyper-parameter tuning algorithm tailored to applications' diverse system requirements in FL training. FedTune iteratively adjusts FL hyper-parameters during FL training and can be easily integrated into existing FL systems. Through extensive evaluations of FedTune for diverse applications and FL aggregation algorithms, we show that FedTune is lightweight and effective, achieving 8.48%-26.75% system overhead reduction compared to using fixed FL hyper-parameters. This paper assists FL practitioners in designing high-performance FL training solutions. The source code of FedTune is available at https://github.com/DataSysTech/FedTune.

cs.LG↗

arXiv2022

Proof of User Similarity: the Spatial Measurer of Blockchain

Although proof of work (PoW) consensus dominates the current blockchain-based systems mostly, it has always been criticized for the uneconomic brute-force calculation. As alternatives, energy-conservation and energy-recycling mechanisms heaved in sight. In this paper, we propose proof of user similarity (PoUS), a distinct energy-recycling consensus mechanism, harnessing the valuable computing power to calculate the similarities of users, and enact the calculation results into the packing rule. However, the expensive calculation required in PoUS challenges miners in participating, and may induce plagiarism and lying risks. To resolve these issues, PoUS embraces the best-effort schema by allowing miners to compute partially. Besides, a voting mechanism based on the two-parties computation and Bayesian truth serum is proposed to guarantee privacy-preserved voting and truthful reports. Noticeably, PoUS distinguishes itself in recycling the computing power back to blockchain since it turns the resource wastage to facilitate refined cohort analysis of users, serving as the spatial measurer and enabling a searchable blockchain. We build a prototype of PoUS and compare its performance with PoW. The results show that PoUS outperforms PoW in achieving an average TPS improvement of 24.01% and an average confirmation latency reduction of 43.64%. Besides, PoUS functions well in mirroring the spatial information of users, with negligible computation time and communication cost.

cs.CR↗

arXiv2022

DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization

A large amount of high-dimensional and heterogeneous data appear in practical applications, which are often published to third parties for data analysis, recommendations, targeted advertising, and reliable predictions. However, publishing these data may disclose personal sensitive information, resulting in an increasing concern on privacy violations. Privacy-preserving data publishing has received considerable attention in recent years. Unfortunately, the differentially private publication of high dimensional data remains a challenging problem. In this paper, we propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases: a Markov-blanket-based attribute clustering phase and an invariant post randomization (PRAM) phase. Specifically, splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable allocation of privacy budget, while a double-perturbation mechanism satisfying local differential privacy facilitates an invariant PRAM to ensure no loss of statistical information and thus significantly preserves data utility. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy. We conduct extensive experiments on four real-world datasets and the experimental results demonstrate that our mechanism can significantly improve the data utility of the published data while satisfying differential privacy.

cs.CR↗

arXiv2022

zk-PCN: A Privacy-Preserving Payment Channel Network Using zk-SNARKs

Payment channel network (PCN) is a layer-two scaling solution that enables fast off-chain transactions but does not involve on-chain transaction settlement. PCNs raise new privacy issues including balance secrecy, relationship anonymity and payment privacy. Moreover, protecting privacy causes low transaction success rates. To address this dilemma, we propose zk-PCN, a privacy-preserving payment channel network using zk-SNARKs. We prevent from exposing true balances by setting up \textit{public balances} instead. Using public balances, zk-PCN can guarantee high transaction success rates and protect PCN privacy with zero-knowledge proofs. Additionally, zk-PCN is compatible with the existing routing algorithms of PCNs. To support such compatibility, we propose zk-IPCN to improve zk-PCN with a novel proof generation (RPG) algorithm. zk-IPCN reduces the overheads of storing channel information and lowers the frequency of generating zero-knowledge proofs. Finally, extensive simulations demonstrate the effectiveness and efficiency of zk-PCN in various settings.

cs.CR↗

arXiv2022

MalFox: Camouflaged Adversarial Malware Example Generation Based on Conv-GANs Against Black-Box Detectors

Deep learning is a thriving field currently stuffed with many practical applications and active research topics. It allows computers to learn from experience and to understand the world in terms of a hierarchy of concepts, with each being defined through its relations to simpler concepts. Relying on the strong capabilities of deep learning, we propose a convolutional generative adversarial network-based (Conv-GAN) framework titled MalFox, targeting adversarial malware example generation against third-party black-box malware detectors. Motivated by the rival game between malware authors and malware detectors, MalFox adopts a confrontational approach to produce perturbation paths, with each formed by up to three methods (namely Obfusmal, Stealmal, and Hollowmal) to generate adversarial malware examples. To demonstrate the effectiveness of MalFox, we collect a large dataset consisting of both malware and benignware programs, and investigate the performance of MalFox in terms of accuracy, detection rate, and evasive rate of the generated adversarial malware examples. Our evaluation indicates that the accuracy can be as high as 99.0% which significantly outperforms the other 12 well-known learning models. Furthermore, the detection rate is dramatically decreased by 56.8% on average, and the average evasive rate is noticeably improved by up to 56.2%.

cs.CR↗