Search

Domain generalization aims to learn a domain-invariant representation from multiple source domains so that a model can generalize well across unseen target domains. Such models are often trained with examples that are presented randomly from all source domains, which can make the training unstable due to optimization in conflicting gradient directions. Here, we explore inter-domain curriculum learning (IDCL) where source domains are exposed in a meaningful order to gradually provide more complex ones. The experiments show that significant improvements can be achieved in both PACS and Office-Home benchmarks, and ours improves the state-of-the-art method by 1.08%.

Vehicle re-identification (Re-ID) methods often fail to achieve robust performance due to insufficient training data and domain diversities. Although state-of-the-art methods apply image-to-image translation or web data to achieve data augmentation, the construct of new datasets will not only introduce noise, but also undergo a mismatch issue with the source domain. Moreover, the label noise of cross-domain data in existing label distribution technologies cannot be alleviated. In this paper, a multi-domain joint learning with inter-domain adaptation label smoothing regularization (IALSR) is proposed using a semi-supervised learning framework. The overall framework consists of two parts. In one part, a multi-domain joint network (MJNet) is proposed to learn multiple vehicle attributes simultaneously. The output of the training model is employed to group several inter-domain subsets, which are regarded as different domains. To adapt to domain diversities, style transfer models are learned for each pair of subsets to generate free and rich data as a novel data augmentation approach. In the other part, IALSR, which preserves self-similarity and domain-transitivity, is designed to smooth the noise of style-transferred data. Upon our basis, we further introduce the web data to verify the superiority of the IALSR. The results of extensive experimental on two large-scale vehicle Re-ID datasets demonstrate that the proposed approach is superior to other state-of-the-art ones.

This paper presents an inter-domain transport net-work slice management with Service Level Agreements (SLA) using the ETSI TeraFlowSDN (TFS) controller. Different instances of the TFS controller are deployed for each involved domain. The communication between the TFS instances is supported by a Distributed Ledger Technology (DLT)-based database. The different TFS instances upload the abstracted view of their topologies and retrieve that from remote peers. When the end-To-end SLA of the transport network slice is violated, the slice is reconfigured avoiding the domain that originated the violation. © 2022 IEEE.

Internet of Things (IoT) is one of the heterogeneous network consists of vast number of connected devices. These networks need smart architecture to accommodate the expected increase of data generation. Software-Defined Networks (SDN) have gained popularity as a key enabler for automated provisioning and ease in IoT network resources management. For ubiquitous coverage, these network involve seamless handoff of the user devices ensuring the provision the services as per user demand. Although the basic inter-domain handoff rules exist in the next SDN domain are not sufficient to provide the primary domain services to the IoT networks. This issue leads to degradation of post-handover performance. In this paper, the SDN based Heterogeneous Inter-Domain Handoff system for IoT (SDN-HIIoT) is proposed that enables SDN-Controller to exchange flow rules by using the East/West application programming interface. The proposed system is using a process of hybrid flow rules execution on heterogeneous SDN domain for provision of Quality of Services (QoS) to mobile users the same as the primary domain. Experiment results are provided to demonstrate the proposed system can significantly improve the post-handoff performance and provides ubiquitous services.

The inter-domain routing with BGP is highly vulnerable to malicious attacks, due to the lack of a secure means of verifying authenticity and legitimacy of inter-domain routes. Resource Public Key Infrastructure (RPKI) is a new security infrastructure to prevent the most devastating prefix hijacks in BGP by maintaining a Route Origin Authorization (ROA) repository. However, RPKI is a centralized hierarchical architecture that may empower the centralized authorities to unilaterally revoke or compromise any IP prefixes under their control. To eliminate the risks of RPKI, we present ROAchain, a novel BGP security infrastructure based on blockchain. Different from RPKI, ROAchain is a decentralized architecture, in which each AS maintains a globally consistent and tamper-proof ROA repository, authenticating the legitimacy of route origin and preventing BGP prefix hijacks. To ensure the strong consistency, scalability, and security of ROAchain, a novel consensus algorithm is proposed, in which the credence value, collective signing, sharding, and a penalty mechanism are introduced. Moreover, a compatibility design is proposed without changing the current BGP protocol. Finally, ROAchain is implemented in Golang and validated on the Google Cloud.

The integrated LTE and WLAN Networks provide flexibility to use the Internet in Rural areas of India where their network infrastructure is not available. The research article focus to provide Internet service to the rural area end-users with a certain level of defined QoS as per ITU and TRAI guidelines. The selection of the best-suited routing protocol may have the capacity to help to achieve our objective. In the integrated network, it is much common to use a diverse variety of inter-domain routing protocol for forwarding packets by routing table updates. These tables are part of the memory of routers that help to forward packets from source to destination using their routing algorithms so that more users may experience QoS. This paper evaluates the performance of Bellman BGPv4, Inter OSPFv2, and Inter RIPv2 in terms of Routing Overhead for the integrated networks under a virtual QualNet 9.1 network simulator scenario.

Software-Defined Networking has become an integral technology for large scale networks that require dynamic flow management. It separates the control function from data plane devices and centralizes it in a domain controller. However, only a limited number of switches can be managed by a single and centralized controller which introduces challenges such as scalability, reliability, and availability. Distributed controller architecture resolves these issues but also introduces new challenges of uneven load and traffic management across domains. As real-world networks have redundant links, hence a significant challenge is to distribute traffic flows on multiple paths, within a domain, and across multiple independent domains. The selection of ingress and egress switches becomes even more problematic if the intermediate domain is non-cooperative. In this work, we propose a Dynamically Optimized and Load-balanced Path for Inter-domain (DOLPHIN) communication system, a customized solution for different SDN controllers. It provides control beyond the virtual switch elements in intra and inter-domain communication and extends the range of programmability to wireless devices, such as the Internet of Things or vehicular networks. Extensive simulation results show that the traffic load is distributed evenly on multiple links connecting different domains. We model data center communication and 5G vehicular network communication to show that, by load balancing the flow completion times of the different types of network traffic can be significantly improved.

Active Queue Management (AQM) has been considered as a paradigm for the complicated network management task of mitigating congestion by controlling buffer of network link queues. However, finding the right parameters for an AQM scheme is very challenging due to the dynamics of the IP networks. In addition, this problem becomes even more complex in inter-domain scenarios where several organizations interconnect each other with the limitation of not sharing raw and private data. As a result, existing AQM schemes have not been widely employed despite their advantages. Therefore, we present a solution that tackles the challenges of tuning the AQM parameters for inter-domain congestion control scenarios where the network management goes beyond an organization’s domain. We then introduce the Federated Intelligence for AQM (FIAQM) architecture, which enhances the existing AQM schemes by leveraging the Federated Learning approach. The proposed FIAQM framework is capable of dynamically adjusting the AQM parameters in a multi-domain setting, which is hard to achieve with the conventional AQM solutions working alone. To this end, FIAQM uses an artificial neural network, trained in a federated manner, to predict beyond-own-domain congestion and an intelligent AQM parameter tuner. The evaluation results show that FIAQM can effectively improve the performance of the inter-domain connections by reducing the congestion on their links while preserving the network data private within each participating domain.

The very nature of scientific inquiry encourages the flow of ideas across research domains in a discipline. Research topics with higher inter-domain presence tend to attract higher attention at individual and organizational levels. This is more pronounced in a discipline like computing, with its deeply intertwined ideas and strong connections with technology. In this paper, we study corpora of research publications across four domains of the computing discipline – covering more than 150,000 papers, involving more than 200,000 authors over 55 years and 175 publication venues – to examine the influences on inter-domain presence of research topics. We find statistically significant evidence that higher collective eminence of researchers publishing on a topic is related to lower inter-domain presence of that topic, fewer authors publishing on a topic relate to the topic being likely to have higher inter-domain presence, while topics belonging to more close-knit clusters of topics are likely to have lower inter-domain presence. Our results can inform decisions around defining and sustaining research agendas and offer insights on the progression of the computing discipline.

Face recognition in the unconstrained environment is an ongoing research challenge. Although several covariates of face recognition such as pose and low resolution have received significant attention, “disguise” is considered an onerous covariate of face recognition. One of the primary reasons for this is the scarcity of large and representative labeled databases, along with the lack of algorithms that work well for multiple covariates in such environments. In order to address the problem of face recognition in the presence of disguise, the paper proposes an active learning framework termed as A2-LINK. Starting with a face recognition machine-learning model, A2-LINK intelligently selects training samples from the target domain to be labeled and, using hybrid noises such as adversarial noise, fine-tunes a model that works well both in the presence and absence of disguise. Experimental results demonstrate the effectiveness and generalization of the proposed framework on the DFW and DFW2019 datasets with state-of-the-art deep learning featurization models such as LCSSE, ArcFace, and DenseNet.

In recent years, with the continuous expansion of metropolitan area networks, the routing security problem has become more and more serious. In particular, promise-violating attack to inter-domain routing protocol is one of the most difficult attacks to defend, which always leads to serious consequences, such as maliciously attracting traffic and disrupting the network. To deal with such attack, current research generally adopts routing verification. However, it can only detect attacks violating a specific routing policy triggered by one malicious node, and no research has yet solved the problem caused by multiple collusion nodes. In this paper, we propose BRVM, a blockchain-based routing verification model, to address the issue that violating the shortest AS Path policy. The main idea of BRVM is to construct a route proof chain to verify whether a route violates the policy with the help of the blockchain technology. The precondition that avoiding the collusion attack is that the proportion of the malicious verification nodes is lower than the fault tolerance rate of the consensus algorithm. Then, we prove the correctness of BRVM in theory, and implement a prototype based on Quagga and Hyperledger Fabric. Some experiments on this prototype show that BRVM can indeed solve the promise-violating problem caused by multiple collusion nodes, and about 15.5% faster in performance compared with SPIDeR.

The human ceruloplasmin (hCP) is the copper containing ferroxidase enzyme with multifunctional activities (NO-oxidase, NO2-synthase,oxidation of neurotransmitters including antioxidants). Therefore, it is of interest to probe the multi-domain hCP using moleculardynamics simulation. Results explain the role played by several conserved water centers in the intra and inter-domain recognition throughH-bond interaction with the interacting residues. We observed seventeen conserved water centers in the inter-domain recognition. Weshow that five invariant water centers W13, W14, W18, W23 and W26 connect the Domain 5 to Domain 4 (D5…W…W4). We also show thatfive other water centers W19, W20, W27, W30 and W31 connects the Domain 5 to Domain 6 (D5…W…W6) that is unique in the simulatedform. The W7 and W32 water centers are involved in the D1…W…W6 recognition. This is important for the water-mediated interaction ofGlu1032 to the trinuclear copper cluster present at the interface between these domains. The involvement of W10 water center in theD3…W10…D4 recognition through Gln552…W10…His667 H-bond interaction is critical in the complexation of CP with myeloperoxidase(Mpo). These observations provide insights to the molecular recognition of hCP with other biomolecules in the system.

Debugging a traditional network is notoriously difficult due to network devices’ heterogeneity and protocols’ decentralized nature, but Software-Defined Networking (SDN) is changing this predicament. Recent works have provided very nice approaches for an administrator to perform several fundamental network tests in a single-domain SDN network. However, how to perform these tests securely in multi-domain networks still remains open. In this paper, we study the highly challenging problem of inter-domain forwarding loop test in a SDN environment. We present two novel testing protocols that can be used for inter-domain loop tests. Both protocols are secure in the sense that they protect each domain's private information about its topology and configuration. The first protocol, based on random sampling, is highly efficient with a small error probability diminishing exponentially in the sample size. The second protocol, based on secure set intersection test, guarantees 100 percent accuracy of the result, although not as efficient as the first one. We provide rigorous proofs for the security and accuracy guarantees, and show our protocols have very good efficiency by testing them with real-world network data.

In this letter, we propose a novel transfer learning approach, which simultaneously exploits the intra-domain differentiation and inter-domain correlation to comprehensively solve the drawbacks many existing transfer learning methods suffer from, i.e., they either are unable to handle the negative samples or have strict assumptions on the distribution. Specifically, the sample selection strategy is introduced to handle negative samples by using the local geometry structure and the label information of source samples. Furthermore, the pseudo target label is imposed to slack the assumption on the inter-domain distribution for considering the inter-domain correlation. Then, an efficient alternating iterative algorithm is proposed to solve the formulated optimization problem with multiple constraints. The extensive experiments conducted on eleven real-world datasets show the superiority of our method over state-of-the-art approaches, i.e., our method achieves 11.23% improvement on the MNIST dataset.

Graphical abstract, Highlights • Dynamics and allosteric potentials of the RFTS domain are proposed. • Hinge sites located at the RFTS-CD interface are key regulators for inter-domain interactions. • Network analysis reveals local allosteric networks and inter-domain communication pathways in DNMT1. • A potential allosteric site at the TRD interface for DNMT1 is identified., DNA methyltransferase 1 (DNMT1), a large multidomain enzyme, is believed to be involved in the passive transmission of genomic methylation patterns via methylation maintenance. Yet, the molecular mechanism of interaction networks underlying DNMT1 structures, dynamics, and its biological significance has yet to be fully characterized. In this work, we used an integrated computational strategy that combined coarse-grained and atomistic simulations with coevolution information and network modeling of the residue interactions for the systematic investigation of allosteric dynamics in DNMT1. The elastic network modeling has proposed that the high plasticity of RFTS has strengthened the correlated behaviors of DNMT1 structures through the hinge sites located at the RFTS-CD interface, which mediate the collective motions between domains. The perturbation response scanning (PRS) analysis combined with the enrichment analysis of disease mutations have further highlighted the allosteric potential of the RFTS domain. Furthermore, the long-range paths connect the intra-domain interactions through the TRD interface and catalytic interface, emphasizing some key inter-domain interactions as the bridges in the global allosteric regulation of DNMT1. The observed interplay between conserved intra-domain networks and dynamical plasticity encoded by inter-domain interactions provides insights into the intrinsic dynamics and functional evolution, as well as the design of allosteric modulators of DNMT1 based on the TRD interface.

Path aware networking (PAN) is a promising approach that enables endpoints to participate in end-to-end path selection. PAN unlocks numerous benefits, such as fast failover after link failures, application-based path selection and optimization, and native interdomain multi-path. The utility of PAN hinges on the availability of a large number of high-quality path options. In an inter-domain context, two core questions arise. Can we deploy such an architecture natively in today's Internet infrastructure without creating an overlay relying on BGP? Can we build a scalable multi-path routing system that provides a large number of high-quality paths? We first report on the real-world native deployment of the SCION next-generation architecture, providing a usable PAN infrastructure operating in parallel to today's Internet. We then analyze the scalability of the architecture in an Internet-scale topology. Finally, we introduce a new routing approach to further improve scalability.

Guarantees for traffic traversing the public Internet are hard to come by, as service-level agreements are typically only available for traffic within a single autonomous system or towards direct neighbors. This deficiency leads to unpredictable performance already under normal conditions and can cause outages in the face of networklevel distributed-denial-of-service (DDoS) attacks. In this paper, we present an architecture achieving guaranteed bandwidth properties for global inter-domain network traffic. The control plane of our architecture is based on a distributed server infrastructure, while the data plane enables efficient packet forwarding on per-flow stateless routers. Our implementation demonstrates the technical feasibility and scalability of the design.

Inter-domain routing systems is an important complex network in the Internet. Research on the vulnerability of inter-domain routing network nodes is of great support to the stable operation of the Internet. For the problem of node vulnerability, we proposed a method for identifying key nodes in inter-domain routing systems based on cascading failures (IKN-CF). Firstly, we analyzed the topology of inter-domain routing network and proposed an optimal valid path discovery algorithm considering business relationships. Then, the reason and propagation mechanism of cascading failure in the inter-domain routing network were analyzed, and we proposed two cascading indicators, which can approximate the impact of node failure on the network. After that, we established a key node identification model based on improved entropy weight TOPSIS (EWT), and the key node sequence in the network can be obtained through EWT calculation. We compared the existing three methods in two real inter-domain routing networks. The results indicate that the ranking results of IKN-CF are high accuracy, strong stability, and wide applicability. The accuracy of the top 100 nodes of the ranking result can reach 83.6%, which is at least 12.8% higher than the average accuracy of the existing three methods.

Well-known issues with multicast have prevented the deployment of multicast in 802.11 and other local-area wireless environments. This document offers guidance on known limitations and problems with wireless multicast. Also described are certain multicast enhancement features that have been specified by the IETF and by IEEE 802 for wireless media, as well as some operational choices that can be taken to improve the performace of the network. Finally, some recommendations are provided about the usage and combination of these features and operational choices.

Inter-domain communication in time-sensitive networks (TSN) has been identified as a requirement for various use cases. The TSN Toolbox provides standards for dynamic stream reservations, which is needed for, e.g., batch size 1 production, but these standards do not support the interaction on the control plane between multiple TSN domains. This paper presents control plane mechanisms for multi-domain time sensitive networks (MDTSNs) integrating an east–westbound protocol in the existing TSN control plane, in order to achieve multi-domain on-demand end-to-end bounded-latency TSN streams. Solutions for issues resulting from MDTSN, particularly the inter-domain forwarding offset, are presented. A proof of concept has been implemented and evaluated in a physical MDTSN test environment in order to prove the viability of the mechanisms developed.

As industrial control systems are becoming increasingly interconnected, there is a rising need for secure and highly available communication as a commodity product. We introduce Linc, a communication gateway that leverages SCION, a next-generation Internet architecture to provide highly reliable and secure inter-domain connectivity for industrial applications.