Optimizing the monitoring of network traffic features to detect abnormal traffic is critical. We propose a two-stage monitoring and classification (MOCA) system requiring fewer features to detect and classify malicious network attacks. The first stage monitors abnormal traffic, and the anomalous traffic is forwarded for processing in the second stage. A small subset of features trains both classifiers. We demonstrate MOCA’s effectiveness in identifying attacks in the CICIDS2017 dataset with an accuracy of 99.84% and in the CICDDOS2019 dataset with an accuracy of 93%, which significantly outperforms previous methods. We also found that MOCA can use a pre-trained classifier with one feature to distinguish DDoS and Botnet attacks from normal traffic in four different datasets. Our measurements show that MOCA can distinguish DDoS attacks from normal traffic in the CICDDOS2019 dataset with an accuracy of 96% and DDoS attacks in non-IoT and IoT traffic with an accuracy of 99.94%. The results emphasize the importance of using connection features to discriminate new DDoS and Bot attacks from benign traffic, especially with insufficient training samples.
20 January 2016 in Journal of Internet Services and Applications
Fault localization for SDN becomes one of the most critical but difficult tasks. Existing tools typically only address a specific part of the problem (e.g., control plane verification, flow checker). In this paper, we propose a new approach to tackle SDN fault localization by automatically Modeling via Policy Inference (called MPI) the causality between SDN faults and their symptoms to a belief network. In the MPI system, a service oriented high level policy language is used to specify network services provisioned between end nodes. MPI parses each service provisioning policy to a logical policy view, which consists of a pair of logical end nodes, a traffic pattern specification, and a list of required network functions (or a service function chain). An SDN controller takes the policies from multiple parties and provisions the requested services on its orchestrated SDN network. MPI queries the controller about the network topology and retrieves flow rules from all SDN switches. MPI maps the policy view to the corresponding implementation view, in which all the logical components in the policy view are mapped to the actual system components along with the actual network topology. Referring to the component causality graph templates derived from SDN reference model, the implementation view of the current running network services can be modeled as a belief network. A heuristic fault reasoning algorithm is adopted to search for the most likely root causes. MPI has been evaluated in both a simulation environment and a real network system for its accuracy and efficiency. The evaluation shows that MPI is a highly scalable, effective and flexible modeling approach to tackle fault localization challenges in a highly dynamic and agile SDN network.
1 January 2013 in Journal of Internet Services and Applications
Port is a basic parameter in TCP/IP data communication. However, a port by its number has no clear association to the types of applications. Identifying such an association, which is referred to as a port role, provides important information to many network applications such as IDS and traffic shaper, as well as detecting new network services and security attacks. Traditional studies on port role identification are only based on port behavior shown on an individual host, other than jointly viewed macroscopic port behavior embodied by all relevant traffic flows among multiple hosts. Port role identification based on macroscopic behavior can reflect severs or clients to discover new services or attacks in the network. In this paper, we propose a novel port role identification approach called PortView, which is based on fuzzy macroscopic port behavior analysis. In our approach, we design a two-dimensional Macroscopic Port Classification Plane (MPCP) to classify port roles into six role zones using an EM fuzzy clustering algorithm. Comprehensive experiments using real Internet traces from the CERNET network validate that PortView can effectively and accurately identify port role based on its macroscopic port behavior.