Biblio

Network attacks are becoming more intense and characterized by complexity and persistence. Mechanisms that ensure network resilience to faults and threats should be well provided. Different approaches have been proposed to network resilience; however, most of them rely on static policies, which is unsuitable for current complex network environments and real-time requirements. To address these issues, we present a Belief-Desire-Intention (BDI) based multi-agent resilience network controller coupled with blockchain. We first clarify the theory and platform of the BDI, then discuss how the BDI evaluates the network resilience. In addition, we present the architecture, workflow, and applications of the resilience network controller. Simulation results show that the resilience network controller can effectively detect and mitigate distributed denial of service attacks.

Network resilience is crucial to ensure reliable and secure operation of critical infrastructures. Although graph theoretic methods have been developed to quantify the topological resilience of networks, i.e., measuring resilience with respect to connectivity, in this study we propose to use the tools from Topological Data Analysis (TDA), Algebraic Topology, and Optimal Transport (OT). In our prior work, we used these tools to create a resilience metric that bypassed the need to embed a network onto a space. We also hypothesized that embeddings could encode different information about a network and that different embeddings could result in different outcomes when computing resilience. In this paper we attempt to test this hypothesis. We will utilize the WEGL framework to compute the embedding for the considered network and compare the results against our prior work, which did not use an embedding process. To our knowledge, this is the first attempt to study the ramifications of choosing an embedding, thus providing a novel understanding into how to choose an embedding and whether such a choice matters when quantifying resilience.

Software-defined networks (SDN), through their programmability, significantly increase network resilience by enabling dynamic reconfiguration of network topologies in response to faults and potentially malicious attacks detected in real-time. Another key trend in network softwarization is cloud-native software, which, together with SDN, will be an integral part of the core of future 5G networks. In SDN, the control plane forms the "brain" of the software-defined network and is typically implemented as a set of distributed controller replicas to avoid a single point of failure. Distributed consensus algorithms are used to ensure agreement among the replicas on key data even in the presence of faults. Security is also a critical concern in ensuring that attackers cannot compromise the SDN control plane; byzantine fault tolerance algorithms can provide protection against compromised controller replicas. However, while reliability/availability and security form key attributes of resilience, they are typically modeled separately in SDN, without consideration of the potential impacts of their interaction. In this paper we present an initial framework for a model that unifies reliability, availability, and security considerations in distributed consensus. We examine – via simulation of our model – some impacts of the interaction between accidental faults and malicious attacks on SDN and suggest potential mitigations unique to cloud-native software.

Being able to describe a specific network as consistent is a large step towards resiliency. Next to the importance of security lies the necessity of consistency verification. Attackers are currently focusing on targeting small and crutial goals such as network configurations or flow tables. These types of attacks would defy the whole purpose of a security system when built on top of an inconsistent network. Advances in Artificial Intelligence (AI) are playing a key role in ensuring a fast responce to the large number of evolving threats. Software Defined Networking (SDN), being centralized by design, offers a global overview of the network. Robustness and adaptability are part of a package offered by programmable networking, which drove us to consider the integration between both AI and SDN. The general goal of our series is to achieve an Artificial Intelligence Resiliency System (ARS). The aim of this paper is to propose a new AI-based consistency verification system, which will be part of ARS in our future work. The comparison of different deep learning architectures shows that Convolutional Neural Networks (CNN) give the best results with an accuracy of 99.39% on our dataset and 96% on our consistency test scenario.

The assessment of networks is frequently accomplished by using time-consuming analysis tools based on simulations. For example, the blocking probability of networks can be estimated by Monte Carlo simulations and the network resilience can be assessed by link or node failure simulations. We propose in this paper to use Artificial Neural Networks (ANN) to predict the robustness of networks based on simple topological metrics to avoid time-consuming failure simulations. We accomplish the training process using supervised learning based on a historical database of networks. We compare the results of our proposal with the outcome provided by targeted and random failures simulations. We show that our approach is faster than failure simulators and the ANN can mimic the same robustness evaluation provide by these simulators. We obtained an average speedup of 300 times.

Enhancing the security and resilience of interdependent infrastructures is crucial. In this paper, we establish a theoretical framework based on Markov decision processes (MDPs) to design optimal resiliency mechanisms for interdependent infrastructures. We use MDPs to capture the dynamics of the failure of constituent components of an infrastructure and their cyber-physical dependencies. Factored MDPs and approximate linear programming are adopted for an exponentially growing dimension of both state and action spaces. Under our approximation scheme, the optimally distributed policy is equivalent to the centralized one. Finally, case studies in a large-scale interdependent system demonstrate the effectiveness of the control strategy to enhance the network resilience to cascading failures.

Cloud computing is a solution to reduce the cost of IT by providing elastic access to shared resources. It also provides solutions for on-demand computing power and storage for devices at the edge networks with limited resources. However, increasing the number of connected devices caused by IoT architecture leads to higher network traffic and delay for cloud computing. The centralised architecture of cloud computing also makes the edge networks more susceptible to challenges in the core network. Fog computing is a solution to decrease the network traffic, delay, and increase network resilience. In this paper, we study how fog computing may improve network resilience. We also conduct a simulation to study the effect of fog computing on network traffic and delay. We conclude that using fog computing prepares the network for better response time in case of interactive requests and makes the edge networks more resilient to challenges in the core network.

The IoT (Internet of Things) is one of the primary reasons for the massive growth in the number of connected devices to the Internet, thus leading to an increased volume of traffic in the core network. Fog and edge computing are becoming a solution to handle IoT traffic by moving timesensitive processing to the edge of the network, while using the conventional cloud for historical analysis and long-term storage. Providing processing, storage, and network communication at the edge network are the aim of fog computing to reduce delay, network traffic, and decentralise computing. In this paper, we define a framework that realises fog computing that can be extended to install any service of choice. Our framework utilises fog nodes as an extension of the traditional switch to include processing, networking, and storage. The fog nodes act as local decision-making elements that interface with software-defined networking (SDN), to be able to push updates throughout the network. To test our framework, we develop an IP spoofing security application and ensure its correctness through multiple experiments.

The deterministic nature of existing routing protocols has resulted into an ossified Internet with static and predictable network routes. This gives persistent attackers (e.g. eavesdroppers and DDoS attackers) plenty of time to study the network and identify the vulnerable (critical) links to plan devastating and stealthy attacks. Recently, Moving Target Defense (MTD) based approaches have been proposed to to defend against DoS attacks. However, MTD based approaches for route mutation are oriented towards re-configuring the parameters in Local Area Networks (LANs), and do not provide any protection against infrastructure level attacks, which inherently limits their use for mission critical services over the Internet infrastructure. To cope with these issues, we extend the current routing architecture to consider end-hosts as routing elements, and present a formal method based agile defense mechanism to embed resiliency in the existing cyber infrastructure. The major contributions of this paper include: (1) formalization of efficient and resilient End to End (E2E) reachability problem as a constraint satisfaction problem, which identifies the potential end-hosts to reach a destination while satisfying resilience and QoS constraints, (2) design and implementation of a novel decentralized End Point Route Mutation (EPRM) protocol, and (3) design and implementation of planning algorithm to minimize the overlap between multiple flows, for the sake of maximizing the agility in the system. Our PlanetLab based implementation and evaluation validates the correctness, effectiveness and scalability of the proposed approach.