The Experts below are selected from a list of 99 Experts worldwide ranked by ideXlab platform

Heng Liu - One of the best experts on this subject based on the ideXlab platform.

  • hgdom heterogeneous graph convolutional networks for malicious Domain detection
    Network Operations and Management Symposium, 2020
    Co-Authors: Xiaoqing Sun, Jiahai Yang, Zhiliang Wang, Heng Liu
    Abstract:

    As a fundamental component of the Internet, Domain Name System (DNS) is widely abused by attackers in various cybercrimes, making malicious Domain detection an essential task in network defenses. However, some well-crafted attacks with tricky techniques can not only bypass blacklists but also make some machine learning-based detection systems infeasible. In this paper, we design HGDom, an accurate and robust malicious Domain detection system based on a heterogeneous graph convolutional network method. First, we jointly analyze Domain features as well as the complex relations among Domains, clients, and IP addresses. To capture richer information, we introduce a Heterogeneous Information Network (HIN) to model the DNS scene. Then, we propose a novel representation method Named MAGCN. With a meta-path-based attention mechanism, it can handle node features and the graph structure in HIN at the same time. To our best knowledge, this is the first work to apply GCN in cyber security analysis. Comprehensive experiments over DNS data from TUNET and CERNET2 are conducted to validate the effectiveness and superiority of our proposed methods. The comparison results show that HGDom outperforms state-of-the-art approaches with promising performance. Besides, the system is decided to be deployed in production to assist with network security management for CERNET2.

Xiaoqing Sun - One of the best experts on this subject based on the ideXlab platform.

  • hgdom heterogeneous graph convolutional networks for malicious Domain detection
    Network Operations and Management Symposium, 2020
    Co-Authors: Xiaoqing Sun, Jiahai Yang, Zhiliang Wang, Heng Liu
    Abstract:

    As a fundamental component of the Internet, Domain Name System (DNS) is widely abused by attackers in various cybercrimes, making malicious Domain detection an essential task in network defenses. However, some well-crafted attacks with tricky techniques can not only bypass blacklists but also make some machine learning-based detection systems infeasible. In this paper, we design HGDom, an accurate and robust malicious Domain detection system based on a heterogeneous graph convolutional network method. First, we jointly analyze Domain features as well as the complex relations among Domains, clients, and IP addresses. To capture richer information, we introduce a Heterogeneous Information Network (HIN) to model the DNS scene. Then, we propose a novel representation method Named MAGCN. With a meta-path-based attention mechanism, it can handle node features and the graph structure in HIN at the same time. To our best knowledge, this is the first work to apply GCN in cyber security analysis. Comprehensive experiments over DNS data from TUNET and CERNET2 are conducted to validate the effectiveness and superiority of our proposed methods. The comparison results show that HGDom outperforms state-of-the-art approaches with promising performance. Besides, the system is decided to be deployed in production to assist with network security management for CERNET2.

Johnson Jeyakumar, Isaac Henderson - One of the best experts on this subject based on the ideXlab platform.

  • Implementation of Distributed Light weight trust infrastructure for automatic validation of faults in an IOT sensor network
    2019
    Co-Authors: Johnson Jeyakumar, Isaac Henderson, Wagner Sven, Roßnagel Heiko
    Abstract:

    The goal of the paper is to design and implement a distributed trust infrastructure, which makes use of the existing Internet Domain Name System (DNS) and its global trust anchor. Since it has high scalability and eases the burden on relying parties in turn, allows for highly efficient queries to support individual trust decisions. In this implementation, a stand-alone private DNS infrastructure including top level Domains was developed with Raspberry Pi Cluster. Further, the security of the DNS for the trust infrastructure is enhanced by implementing DNSSEC and DANE protocol with TLSA resource records. It also includes the core functionality of the LIGHTest infrastructure like developing trust lists, Trust Scheme Publication Authority (TSPA) and a Delegation Publisher (DP). In this paper, a distributed trust infrastructure is developed and visualized practically by designing an infrastructure for validation and authentication of faults in the sensor system of an organization using a Raspberry Pi Cluster

  • Distributed lightweight trust infrastructure with automatic validation for electronic transactions
    2019
    Co-Authors: Johnson Jeyakumar, Isaac Henderson
    Abstract:

    The goal of the thesis is to address solution to security threats faced currently by the transactions among devices in Industry 4.0 network. In order to address the cyber threats a demo version of a distributed light weight trust infrastructure is designed and developed, which makes use of the existing Internet Domain Name System (DNS) and its global trust anchor. Since it has high scalability and eases the burden on relying parties, in turn allows for highly efficient queries to support individual trust decisions. In this demo version a standalone private DNS infrastructure including Top Level Domains has to be developed with Raspberry pi Cluster. Further, the Security of the DNS for the trust infrastructure is enhanced in this demo version by implementing DNSSEC and also DANE Protocol with TLSA Resource Records. It also includes the core functionality of the \gls{lightest} example: Developing Trust Lists, Trust Scheme Publication Authority [7]. In the thesis a demo version of distributed light weight trust infrastructure is developed and visualized practically by designing an infrastructure for validation and authentication of data in the Sensor network of an organization using a Raspberry pi Cluster and also the flexibility of the light weight infrastructure is discussed by considering four important scenarios which can overcome the issues of data authentication in current Industry 4.0 predictive maintenance system. Also two different applications of Block chain technology related to data authentication in Industry 4.0 is discussed. Based on one of the block chain application "the Block chain based PKI management system" an idea is proposed how this can be incorporated into an IOT sensor network for certificate validation. Finally the two technologies block chain and distributed light weight trust infrastructure using DNS are analyzed based on five parameters Namely performance, maintainability, manageability, security and cost

Roßnagel Heiko - One of the best experts on this subject based on the ideXlab platform.

  • LIGHTest: Lightweight Infrastrucutre for Global and Heterogeneous Trust Management
    Universität Tübingen, 2020
    Co-Authors: Roßnagel Heiko, Wagner Sven
    Abstract:

    The EU-funded LIGHTest project is developing a global trust infrastructure that enables an easy and efficient verification process of electronic transactions, even if the involved instances belong to different trust Domains. LIGHTest builds on the available Internet Domain Name System (DNS) infrastructure. This paper gives an overview on the LIGHTest project, its reference architecture and variety of application fields

  • Implementation of Distributed Light weight trust infrastructure for automatic validation of faults in an IOT sensor network
    2019
    Co-Authors: Johnson Jeyakumar, Isaac Henderson, Wagner Sven, Roßnagel Heiko
    Abstract:

    The goal of the paper is to design and implement a distributed trust infrastructure, which makes use of the existing Internet Domain Name System (DNS) and its global trust anchor. Since it has high scalability and eases the burden on relying parties in turn, allows for highly efficient queries to support individual trust decisions. In this implementation, a stand-alone private DNS infrastructure including top level Domains was developed with Raspberry Pi Cluster. Further, the security of the DNS for the trust infrastructure is enhanced by implementing DNSSEC and DANE protocol with TLSA resource records. It also includes the core functionality of the LIGHTest infrastructure like developing trust lists, Trust Scheme Publication Authority (TSPA) and a Delegation Publisher (DP). In this paper, a distributed trust infrastructure is developed and visualized practically by designing an infrastructure for validation and authentication of faults in the sensor system of an organization using a Raspberry Pi Cluster

Wagner Sven - One of the best experts on this subject based on the ideXlab platform.

  • LIGHTest: Lightweight Infrastrucutre for Global and Heterogeneous Trust Management
    Universität Tübingen, 2020
    Co-Authors: Roßnagel Heiko, Wagner Sven
    Abstract:

    The EU-funded LIGHTest project is developing a global trust infrastructure that enables an easy and efficient verification process of electronic transactions, even if the involved instances belong to different trust Domains. LIGHTest builds on the available Internet Domain Name System (DNS) infrastructure. This paper gives an overview on the LIGHTest project, its reference architecture and variety of application fields

  • Implementation of Distributed Light weight trust infrastructure for automatic validation of faults in an IOT sensor network
    2019
    Co-Authors: Johnson Jeyakumar, Isaac Henderson, Wagner Sven, Roßnagel Heiko
    Abstract:

    The goal of the paper is to design and implement a distributed trust infrastructure, which makes use of the existing Internet Domain Name System (DNS) and its global trust anchor. Since it has high scalability and eases the burden on relying parties in turn, allows for highly efficient queries to support individual trust decisions. In this implementation, a stand-alone private DNS infrastructure including top level Domains was developed with Raspberry Pi Cluster. Further, the security of the DNS for the trust infrastructure is enhanced by implementing DNSSEC and DANE protocol with TLSA resource records. It also includes the core functionality of the LIGHTest infrastructure like developing trust lists, Trust Scheme Publication Authority (TSPA) and a Delegation Publisher (DP). In this paper, a distributed trust infrastructure is developed and visualized practically by designing an infrastructure for validation and authentication of faults in the sensor system of an organization using a Raspberry Pi Cluster