IEEE/ACM International Symposium on Quality of Service (IWQoS) 2021
Cloud & Storage
Towards Private Similarity Query based Healthcare Monitoring over Digital Twin Cloud Platform
Yandong Zheng, Rongxing Lu, Yunguo Guan and Songnian Zhang (University of New Brunswick, Canada); Jun Shao (Zhejiang Gongshang University, China)
Secure Outsourced Top-$k$ Selection Queries against Untrusted Cloud Service Providers
Xixun Yu (Xidian University, China & University of Delaware, USA); Yidan Hu and Rui Zhang (University of Delaware, USA); Zheng Yan (Xidian University & Aalto University, China); Yanchao Zhang (Arizona State University, USA)
EC-Scheduler: A Load-Balanced Scheduler to Accelerate the Straggler Recovery for Erasure Coded Storage Systems
Xinzhe Cao, Gen Yang, Yunfei Gu and Chentao Wu (Shanghai Jiao Tong University, China); Jie Li (Shanghai Jiaotong University, China); Guangtao Xue and Minyi Guo (Shanghai Jiao Tong University, China); Yuanyuan Dong and Yafei Zhao (Alibaba Group, China)
To address the above problem, we propose a dynamic load-balanced scheduling algorithm for straggler recovery called EC-Scheduler. EC-Scheduler adjusts the recovery schedule dynamically with the awareness of continuous load fluctuation on the nodes, guaranteeing high parallelism and load balance ability simultaneously. To demonstrate the effectiveness of EC-Scheduler, we conduct several experiments in a cluster. The results show that, compared to typical recovery schemes such as Fast-PR and EC-Store, EC-Scheduler could achieve a 1.3X speed-up in the recovery process and 10X improvement in recovery load imbalance factor.
A Proactive Failure Tolerant Mechanism for SSDs Storage Systems based on Unsupervised Learning
Hao Zhou, Zhiheng Niu, Gang Wang and Xiaoguang Liu (Nankai University, China); Dongshi Liu, Bingnan Kang, Hu Zheng and Yong Zhang (Huawei, China)
In this paper, we propose a proactive failure tolerance mechanism for SSDs storage systems based on unsupervised technology. It only uses data of normal SSDs to train the failure prediction model, which means that our method is not limited by the imbalance in SSDs data. At the core of our method is the idea to use VAE-LSTM to learn the pattern of normal SSDs, in which case faulty SSDs can be alerted when their patterns are very different from normal ones. Our method can provide early warning of failures, thereby effectively protecting data and improving the quality of cloud storage service. We also propose a drive failure cause location mechanism, which can help operators analyze the modes of failure by providing guiding suggestions. In order to evaluate the effectiveness of our method, we use cross-validation and online testing methods on SSDs data from a technology company. The results show that the FDR and FAR of our method outperform the baselines by 17.25% and 2.39% on average.
System & Memory
Supporting Flow-Cardinality Queries with O(1) Time Complexity in High-speed Networks
Qingjun Xiao (SouthEast University of China, China); Xiongqin Hu (Southeast University, China); Shigang Chen (University of Florida, USA)
Practical Root Cause Localization for Microservice Systems via Trace Analysis
Zeyan Li (Tsinghua University, China); Junjie Chen (Tianjin University, China); Rui Jiao and Nengwen Zhao (Tsinghua University, China); Zhijun Wang, Shuwei Zhang, Yanjun Wu, Long Jiang and Leiqin Yan (China Minsheng Bank, China); Zikai Wang (Bizseer, China); Zhekang Chen (BizSeer, China); Wenchi Zhang (Bizseer Technology Co., Ltd., China); Xiaohui Nie (Tsinghua University, China); Kaixin Sui (Bizseer Technology Co., Ltd., China); Dan Pei (Tsinghua University, China)
Load Balancing in Heterogeneous Server Clusters: Insights From a Product-Form Queueing Model
Mark van der Boor and Céline Comte (Eindhoven University of Technology, The Netherlands)
AIR: An AI-based TCAM Entry Replacement Scheme for Routers
Yuchao Zhang and Peizhuang Cong (Beijing University of Posts and Telecommunications, China); Bin Liu (Tsinghua University, China); Wendong Wang (Beijing University of Posts and Telecommunications, China); Ke Xu (Tsinghua University, China)
Traffic Analytics & Engineering
Byte-Label Joint Attention Learning for Packet-grained Network Traffic Classification
Kelong Mao (Tsinghua University, China); Xi Xiao (Graduate School at Shenzhen, Tsinghua University, China); Guangwu Hu (Shenzhen Institute of Information Technology, China); Xiapu Luo (The Hong Kong Polytechnic University, Hong Kong); Bin Zhang (Peng Cheng Laboratory, China); Shutao Xia (Tsinghua University, China)
In this paper, we devise a new method, called BLJAN, to jointly learn from byte sequence and labels for packet-grained traffic classification. BLJAN embeds the packet's bytes and all labels into a joint embedding space to capture their implicit correlations with a dual attention mechanism. It finally builds a more powerful packet representation with an enhancement from label embeddings to achieve high classification accuracy and interpretability. Extensive experiments on two benchmark traffic classification tasks, including application identification and traffic characterization, with three real-world datasets, demonstrate that BLJAN can achieve high performance (96.2%, 96.7%, and 99.7% Macro F1-scores on three datasets) for packet-grained traffic classification, outperforming six representative state-of-the-art baselines in terms of both accuracy and detection speed.
DarkTE: Towards Dark Traffic Engineering in Data Center Networks with Ensemble Learning
Renhai Xu (Tianjin University, China); Wenxin Li (Hong Kong University of Science and Technology); Keqiu Li and Xiaobo Zhou (Tianjin University, China); Heng Qi (Dalian University of Technology, China)
BCAC: Batch Classifier based on Agglomerative Clustering for traffic classification in a backbone network
Hua Wu, Xiying Chen, Guang Cheng, Xiaoyan Hu and Youqiong Zhuang (Southeast University, China)
Efficient Fine-Grained Website Fingerprinting via Encrypted Traffic Analysis with Deep Learning
Meng Shen, Zhenbo Gao and Liehuang Zhu (Beijing Institute of Technology, China); Ke Xu (Tsinghua University, China)
In this paper, we propose BurNet, a fine-grained WF method using Convolutional Neural Networks (CNNs). To extract differences of similar webpages, we propose a new concept named unidirectional burst, which is a sequence of packets corresponding to a piece of HTTP message. BurNet takes as input unidirectional burst sequences, instead of bidirectional packet sequences, which makes it applicable to different attack scenarios. BurNet employs CNNs to build a powerful classifier, where sophisticated architecture is designed to improve classification accuracy while reducing time complexity in training. We collect real-world datasets from three well-known websites and conduct extensive experiments to evaluate the performance of BurNet. The closed-world evaluation results show that BurNet outperforms the stateof-the-art methods in both attack scenarios. In the more realistic open-world setting, BurNet can achieve 0.99 precision and 0.99 recall. BurNet is also superior to its CNN-based counterparts in terms of training efficiency.
Privacy-Preserving Optimal Recovering for the Nearly Exhausted Payment Channels
Minze Xu, Yuan Zhang, Fengyuan Xu and Sheng Zhong (Nanjing University, China)
In this paper, we propose OPRE, a protocol for OPtimal off-chain REcovering of payment channels, to solve this problem. It is optimal in that it recovers the maximum number of nearly exhausted channels in the PCN. Furthermore, we consider users' privacy concerns and design a privacy-preserving version of this protocol, so that users' balance information does not need to be revealed. This protocol maintains optimality in recovering payment channels while providing cryptographically strong privacy guarantee. In addition to the theoretical design and analysis, we also implement OPRE and experimentally evaluate its performance. The results show that the OPRE protocol is both efficient and effective.
Privacy-Preserving Approximate Top-k Nearest Keyword Queries over Encrypted Graphs
Meng Shen and Minghui Wang (Beijing Institute of Technology, China); Ke Xu (Tsinghua University, China); Liehuang Zhu (Beijing Institute of Technology, China)
In this paper, we propose a new graph encryption scheme Aton, which enables efficient and privacy-preserving k-NK querying. Based on the symmetric-key encryption and particular pseudo-random functions, we construct a secure k-NK query index. Aton is built on a ciphertext sum comparison scheme which can achieve approximate distance comparison with high accuracy. Rigorous security analysis proves that it is CQA-2 secure. Experiments with real-world datasets demonstrate that it can efficiently answer k-NK queries with more accurate results compared with the state-of-the-art.
A Behavior Privacy Preserving Method towards RF Sensing
Jianwei Liu (Zhejiang University & Xi'an Jiaotong University, China); Chaowei Xiao (University of Michigan, ann arbor, USA); Kaiyan Cui (Xi'an Jiaotong University & The Hong Kong Polytechnic University, China); Jinsong Han (Zhejiang University & School of Cyber Science and Technology, China); Xian Xu and Kui Ren (Zhejiang University, China); Xufei Mao (Dongguan University of Tech, China)
In this paper, we propose a privacy-preserving deep neural network named BPCloak to erase the behavior information in RF signals while retaining the ability of user authentication. We conduct extensive experiments over mainstream RF signals collected from three real wireless systems, including the WiFi, Radio Frequency IDentification (RFID), and millimeter-wave (mmWave) systems. The experimental results show that BPCloak significantly reduces the behavior recognition accuracy, i.e., 85%+, 75%+, and 65%+ reduction for WiFi, RFID, and mmWave systems respectively, merely with a slight penalty of accuracy decrease when using these three systems for user authentication, i.e., 1%-, 3%-, and 5%-, respectively.
Differential Privacy-Preserving User Linkage across Online Social Networks
Xin Yao (Central South University & Arizona State University, China); Rui Zhang (University of Delaware, USA); Yanchao Zhang (Arizona State University, USA)