Mission critical systems deployed in data centers today are facing more sophisticated failures. Byzantine fault tolerant (BFT) protocols are capable of masking these types of failures, but are rarely deployed due to their performance cost and complexity. In this work, we propose a new approach to designing high performance BFT protocols in data centers. By re-examining the ordering responsibility between the network and the BFT protocol, we advocate a new abstraction offered by the data center network infrastructure. Concretely, we design a new authenticated ordered multicast primitive (AOM) that provides transferable authentication and non-equivocation guarantees. Feasibility of the design is demonstrated by two hardware implementations of AOM -- one using HMAC and the other using public key cryptography for authentication -- on new-generation programmable switches. We then co-design a new BFT protocol, Matrix, that leverages the guarantees of AOM to eliminate cross-replica coordination and authentication in the common case. Evaluation results show that Matrix outperforms state-of-the-art protocols on both latency and throughput metrics by a wide margin, demonstrating the benefit of our new network ordering abstraction for BFT systems.
相關內容
Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based on auto-tuners are not performance effective across the wide range of inputs used in practice. In the present paper, we start an investigation of predictive models based on machine learning techniques in order to optimize Convolution Neural Networks (CNNs). As a use-case, we focus on the ARM Compute Library which provides three different implementations of the convolution operator at different numeric precision. Starting from a collation of benchmarks, we build and validate models learned by Decision Tree and naive Bayesian classifier. Preliminary experiments on Midgard-based ARM Mali GPU show that our predictive model outperforms all the convolution operators manually selected by the library.
Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious correlations, existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features. Nevertheless, ID-based SSL approaches sacrifice the positive impact of invariant features, while feature engineering methods require high-cost human labeling. To address the problems, we aim to automatically mitigate the effect of spurious correlations. This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL. To handle the two challenges, we propose an invariant feature learning framework, which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments. Based on the mask mechanism, we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation. Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models.
We provide a framework consisting of tools and metatheorems for the end-to-end verification of security protocols, which bridges the gap between automated protocol verification and code-level proofs. We automatically translate a Tamarin protocol model into a set of I/O specifications expressed in separation logic. Each such specification describes a protocol role's intended I/O behavior against which the role's implementation is then verified. Our soundness result guarantees that the verified implementation inherits all security (trace) properties proved for the Tamarin model. Our framework thus enables us to leverage the substantial body of prior verification work in Tamarin to verify new and existing implementations. The possibility to use any separation logic code verifier provides flexibility regarding the target language. To validate our approach and show that it scales to real-world protocols, we verify a substantial part of the official Go implementation of the WireGuard VPN key exchange protocol.
Agent-based model (ABM) has been widely used to study infectious disease transmission by simulating behaviors and interactions of autonomous individuals called agents. In the ABM, agent states, for example infected or susceptible, are assigned according to a set of simple rules, and a complex dynamics of disease transmission is described by the collective states of agents over time. Despite the flexibility in real-world modeling, ABMs have received less attention by statisticians because of the intractable likelihood functions which lead to difficulty in estimating parameters and quantifying uncertainty around model outputs. To overcome this limitation, we propose to treat the entire system as a Hidden Markov Model and develop the ABM for infectious disease transmission within the Bayesian framework. The hidden states in the model are represented by individual agent's states over time. We estimate the hidden states and the parameters associated with the model by applying particle Markov Chain Monte Carlo algorithm. Performance of the approach for parameter recovery and prediction along with sensitivity to prior assumptions are evaluated under various simulation conditions. Finally, we apply the proposed approach to the study of COVID-19 outbreak on Diamond Princess cruise ship and examine the differences in transmission by key demographic characteristics, while considering different network structures and the limitations of COVID-19 testing in the cruise.
We present a case study investigating feature descriptors in the context of the analysis of chemical multivariate ensemble data. The data of each ensemble member consists of three parts: the design parameters for each ensemble member, field data resulting from the numerical simulations, and physical properties of the molecules. Since feature-based methods have the potential to reduce the data complexity and facilitate comparison and clustering, we are focusing on such methods. However, there are many options to design the feature vector representation and there is no obvious preference. To get a better understanding of the different representations, we analyze their similarities and differences. Thereby, we focus on three characteristics derived from the representations: the distribution of pairwise distances, the clustering tendency, and the rank-order of the pairwise distances. The results of our investigations partially confirmed expected behavior, but also provided some surprising observations that can be used for the future development of feature representations in the chemical domain.
Ultra-reliable and low-latency communication (URLLC) is one of three major application scenarios of the 5G new radio, which has strict latency and reliability requirements. Contention-based grant-free (GF) access protocols, such as Reactive, K-Repetition, and Proactive, have been proposed for uplink URLLC service. In the GF access, user equipment (UE) resends packet immediately after an unsuccessful transmission such that the latency requirement can be satisfied. Taking Reactive as an example, this paper studies the impact of 1- persistent retransmission (1-pR) on the distribution of user-plane delay. We define the number of UEs that try to send packets in each mini-slot as attempt rate. We show that the 1-pR makes the attempt rate seen by the packet in retransmission larger than that seen by the packet in the first transmission. As a result, the successful probability of retransmission is lower than that of the first transmission. Based on this observation, we derive the distribution of user-plane delay, which also takes into account the delay incurred by queueing process. We demonstrate that whether to include the effect of 1-pR and queueing process in the analysis would have a significant impact on the prediction accuracy of delay distribution.
The statistical analysis of structured spatial point process data where the event locations are determined by an underlying spatially embedded relational system has become a vivid field of research. Despite a growing literature on different extensions of point process characteristics to linear network domains, most software implementations remain restricted to either directed or undirected network structures and are of limited use for the analysis of rather complex real-world systems consisting of both undirected and directed parts. Formalizing the network through a graph theoretic perspective, this paper discusses a complementary approach for the analysis of network-based event data through generic network intensity functions and gives a general introduction to the intensitynet package implemented in R covering both computational details and applications. By treating the edges as fundamental entities, the implemented approach allows the computation of intensities and other related values related to different graph structures containing undirected, directed, or a combination of both edges as special cases. The package includes characteristics for network modeling, data manipulation, intensity estimation, computation of local and global autocorrelation statistics, visualization, and extensions to marked point process scenarios. All functionalities are accompanied by reproducible code examples using the chicago data as toy example to illustrate the application of the package.
Traditional approaches for data anonymization consider relational data and textual data independently. We propose rx-anon, an anonymization approach for heterogeneous semi-structured documents composed of relational and textual attributes. We map sensitive terms extracted from the text to the structured data. This allows us to use concepts like k-anonymity to generate a joined, privacy-preserved version of the heterogeneous data input. We introduce the concept of redundant sensitive information to consistently anonymize the heterogeneous data. To control the influence of anonymization over unstructured textual data versus structured data attributes, we introduce a modified, parameterized Mondrian algorithm. The parameter $\lambda$ allows to give different weight on the relational and textual attributes during the anonymization process. We evaluate our approach with two real-world datasets using a Normalized Certainty Penalty score, adapted to the problem of jointly anonymizing relational and textual data. The results show that our approach is capable of reducing information loss by using the tuning parameter to control the Mondrian partitioning while guaranteeing k-anonymity for relational attributes as well as for sensitive terms. As rx-anon is a framework approach, it can be reused and extended by other anonymization algorithms, privacy models, and textual similarity metrics.
Incompleteness is a common problem for existing knowledge graphs (KGs), and the completion of KG which aims to predict links between entities is challenging. Most existing KG completion methods only consider the direct relation between nodes and ignore the relation paths which contain useful information for link prediction. Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning. In addition, these path-based models always ignore nonlinear contributions of path features for link prediction. To solve these problems, we propose a novel KG completion method named OPTransE. Instead of embedding both entities of a relation into the same latent space as in previous methods, we project the head entity and the tail entity of each relation into different spaces to guarantee the order of relations in the path. Meanwhile, we adopt a pooling strategy to extract nonlinear and complex features of different paths to further improve the performance of link prediction. Experimental results on two benchmark datasets show that the proposed model OPTransE performs better than state-of-the-art methods.
Deep convolutional neural networks (CNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past few years, tremendous progress has been made in this area. In this paper, we survey the recent advanced techniques for compacting and accelerating CNNs model developed. These techniques are roughly categorized into four schemes: parameter pruning and sharing, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and sharing will be described at the beginning, after that the other techniques will be introduced. For each scheme, we provide insightful analysis regarding the performance, related applications, advantages, and drawbacks etc. Then we will go through a few very recent additional successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrix, the main datasets used for evaluating the model performance and recent benchmarking efforts. Finally, we conclude this paper, discuss remaining challenges and possible directions on this topic.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191