More Like this

1. In-network Reinforcement Learning for Attack Mitigation using Programmable Data Plane in SDN

   Ganesan, Aparna; Sarac, Kamil (July 2024, The 33rd International Conference on Computer Communications and Networks (ICCCN 2024))

   The development of reinforcement learning (RL) algorithms has created a paradigm where the agents are trained to learn directly by observing the environment and learning policies to perform tasks autonomously. In the case of network environments, these agents can control and monitor the traffic as well as help preserve the confidentiality, integrity, and availability of resources and services in the network. In the case of software defined networks (SDN), the centralized controller in the control plane has become the single point of failure for the entire network. Reactive routing in SDNs makes such networks vulnerable to denial-of-service (DoS) attacks that aim to overwhelm switch memory and the control channel between SDN switches and controllers. One potential solution to cope with such attacks is to use an intelligent mechanism to detect and block them with minimal performance overhead for the controller and control channel. In this work, we investigate the practicality and effectiveness of a reinforcement learning (RL) approach to cope with DoS attacks in SDN networks that utilize programmable switches. Assuming the existence of a reliable reward function, we demonstrate that an RL-based approach can successfully adapt to the changing nature of attack traffic to detect and mitigate attacks without overwhelming switch memory and the control channel in SDN. 

   more » « less
2. In-network Reinforcement Learning for Attack Mitigation using Programmable Data Plane in SDN

   Ganesan, Aparna; Sarac, Kamil (July 2024, IEEE)

   The development of reinforcement learning (RL) algorithms has created a paradigm where the agents are trained to learn directly by observing the environment and learning policies to perform tasks autonomously. In the case of network environments, these agents can control and monitor the traffic as well as help preserve the confidentiality, integrity, and availability of resources and services in the network. In the case of software defined networks (SDN), the centralized controller in the control plane has become the single point of failure for the entire network. Reactive routing in SDNs makes such networks vulnerable to denial-of-service (DoS) attacks that aim to overwhelm switch memory and the control channel between SDN switches and controllers. One potential solution to cope with such attacks is to use an intelligent mechanism to detect and block them with minimal performance overhead for the controller and control channel. In this work, we investigate the practicality and effectiveness of a reinforcement learning (RL) approach to cope with DoS attacks in SDN networks that utilize programmable switches. Assuming the existence of a reliable reward function, we demonstrate that an RL-based approach can successfully adapt to the changing nature of attack traffic to detect and mitigate attacks without overwhelming switch memory and the control channel in SDN. 

   more » « less
3. Debugging SDN in HPC Environments

   https://doi.org/10.1145/3219104.3229277  

   Hayashida, Mami; Rivera, Sergio; Griffioen, James; Fei, Zongming; Song, Yongwook (July 2018, PEARC '18 Proceedings of the Practice and Experience on Advanced Research Computing)

   HPC networks and campus networks are beginning to leverage various levels of network programmability ranging from programmable network configuration (e.g., NETCONF/YANG, SNMP, OF-CONFIG) to software-based controllers (e.g., OpenFlow Controllers) to dynamic function placement via network function virtualization (NFV). While programmable networks offer new capabilities, they also make the network more difficult to debug. When applications experience unexpected network behavior, there is no established method to investigate the cause in a programmable network and many of the conventional troubleshooting debugging tools (e.g., ping and traceroute) can turn out to be completely useless. This absence of troubleshooting tools that support programmability is a serious challenge for researchers trying to understand the root cause of their networking problems. This paper explores the challenges of debugging an all-campus science DMZ network that leverages SDN-based network paths for high-performance flows. We propose Flow Tracer, a light-weight, data-plane-based debugging tool for SDN-enabled networks that allows end users to dynamically discover how the network is handling their packets. In particular, we focus on solving the problem of identifying an SDN path by using actual packets from the flow being analyzed as opposed to existing expensive approaches where either probe packets are injected into the network or actual packets are duplicated for tracing purposes. Our simulation experiments show that Flow Tracer has negligible impact on the performance of monitored flows. Moreover, our tool can be extended to obtain further information about the actual switch behavior, topology, and other flow information without privileged access to the SDN control plane. 

   more » « less
4. Mitigating the Risks of Supporting Multiple Control Plans in a Production SDN Network: A Use Case

   Bezerra, J.; Ibarra, J.; Schwarz, M.; Freitas, H.; Morgan, H. (January 2017, SBRC/WPEIF 2017)

   The SDN paradigm enables network operators to host multiple control planes in parallel, being an approach to support multiple network services. Supporting multiple control planes over production networks exposes the production environment to potential risks and increases operational complexity. To understand and mitigate these risks, we implemented procedures and tools that resulted in a more reliable network. This paper describes our experience and findings with the support of multiple control planes in a wide-area production network. 

   more » « less
5. Latency and Reliability Aware SDN Controller: A Role Delegation Function as a Service

   https://doi.org/10.1109/ccwc57344.2023.10099225  

   Wobuyaga, Dinah; Arzo, Sisay T; Kumar, Harsh; Granelli, Fabrizio; Devetsikiotis, Michael (March 2023, 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC))

   The emergency of machine type and ultra-reliable low latency communication is imposing stringent constraints for service provisioning. Addressing such constraints is challenging for network and cloud service providers. As a trending paradigm, software-defined networking (SDN) plays a significant role in future networks and services. However, the classical implementation of the SDN controller has limitations in-terms-of latency and reliability since the controller is decoupled from the forwarding device. Several research works have tried to tackle these challenges by proposing solutions such as Devoflow, DIFANE, and hierarchical and distributed controller deployment. Nonetheless, these approaches are not fully addressing these challenges. This paper tries to address the problem of latency and reliability by proposing a dynamic controller role delegation architecture for forwarding devices. To align with the microservice or multi-agent-based service-based architecture, the role delegation function as a service is proposed. The dynamic role delegation enables to predict and (pre-)installed flow rules in the forwarding devices based on various considerations such as network state, packet type, and service's stringent requirements. The proposed architecture is implemented and evaluated for latency and resiliency performance in comparison to the centralized and distributed deployment of the SDN controller. We used ComNetsEmu, a softwarized network emulation tool, to emulate SDN and NFV (Network Function Virtualization). The result indicated a significant decrease in latency and improved resilience in case of failure, yielding better network performance. 

   more » « less