MiTFed: A Privacy Preserving Collaborative Network Attack Mitigation Framework Based on Federated Learning Using SDN and Blockchain

Software-defined networking (SDN) is an innovative network technology. It changed the world of computer networking by providing solutions to many challenges. SDN provides programmability, easy and centralized network management, dynamic configuration, and improved security. Although SDN offers remarkable benefits but it provides centralized network management which is prone to attacks. So, intrusion detection systems (IDS) are essential to detect and prevent security attacks in SDN. Traditional IDS follow a centralized machine learning approach which causes vulnerabilities in IDS. Old-style IDS lack data privacy preservation, and solution for training data unavailability due to privacy. Federated learning (FL) is a distributed machine learning approach which provides a collaborative training approach without data sharing. In FL, training is performed on multiple nodes creating a global model without sharing the data. To address challenges and the limitations of traditional IDS, we proposed a FL based multi class classification IDS for SDN. FL delivers an efficient and scalable solution to address challenges of traditional IDS. The proposed model enhances security of SDN by not requiring the centralization of data. To test the impact and efficiency of proposed model, we used a latest and realistic cybersecurity dataset. We also compared the proposed model with state of art existing multi class classification studies. The results and their comparison with existing studies highlight the potential of proposed model to enhance network security while providing a privacypreserving learning environment for intrusion detection.

Attack-aware Security Function Management

Distributed Denial-of-Service (DDoS) attack has been a “nightmare” for cloud. A countermeasure is to establish an Intrusion Detection and Prevention System (IDPS) for cloud. Nevertheless, current IDPSes fail to achieve the detection and prevention in a flexible and lightweight way. In this paper, we propose a novel scheme of IDPS for overcoming the above problem, termed as Auto-scaling IDPS (AsIDPS). AsIDPS is based on Software-Defined Networking (SDN) and Docker container technologies. It first detects abnormal traffic based on the flow statistics collected in SDN switches in real-time. By the SDN controller, the abnormal traffic will be directed to the created Docker containers with Snort running on them for further detection and clean-up. Particularly, the Docker containers can be automatically scaled out or scaled down on demand. The Snort will also deliver an alert to the SDN controller if it detects attack traffic so as to perform a countermeasure if necessary. Benefitting from the flexible network management offered by SDN and the lightweight Docker container, AsIDPS is able to build a flexible and lightweight defense against DDoS attack in cloud. Based on our prototype implementation, we validate the effectiveness of AsIDPS in defending DDoS attack, and also verify its flexibility and lightweight.

The Internet of Things has completely changed the way we interact with our surroundings. The upsurge in the use of IoT devices has helped us to do and monitor our day-to-day tasks with ease. With the increasing use of IoTs, there also comes their own set of security issues that need to be considered. IoT devices generate vast amounts of data, most of which can be shared or connected to social networking sites or online platforms. Due to malicious activity or attacks in the network, the data can be manipulated. Digital deception poses a significant threat in the era of AI-driven social networks, enabling the spread of misinformation and cyber intrusions at an unprecedented scale. Here comes the role of the intrusion detection system, which helps us to detect and prevent security breaches in IoT. In recent years, it has become a critical issue to secure IoT systems as they are more prone to be hacked. So, it has become very important to develop and optimize our traditional intrusion detection systems. Previously used intrusion detection systems suffered from several limitations, such as centralized data storage, privacy, and security concerns. They require a significant amount of processed data to work effectively according to our criteria. This can be challenging to us in case of very few historical attacks that are not enough to train our systems. To overcome these issues, federated learning-based IDS for IoT systems has been proposed. Federated Learning is a machine learning technique that provides a system that can collaboratively learn a model without sharing its data. In federated learning, the machine learning model is trained on the device itself, and only the updates are pushed to the central server for improvement of the central model. It helps us preserve the privacy of the device and, at the same time, enables us to build and train the central model server that can detect any intrusion attacks. This can also reduce the computational cost of machine training by distributing the work across several devices. Federated learning models can adapt to the changes in the environment as they are designed to continuously learn from the recently generated data from servers and devices in the network. This way, the model can progress over time to better detect the changes in the network traffic.

The rapid growth of Internet of Things (IoT) devices and 5G network capabilities results in a broadened threat landscape and increased the potential of Distributed Denial of Service (DDoS) attacks. Whereas detectors can be signature-based (traditional Intrusion Detection Systems - IDS), they are ineffective against zero-day and complex multi-vector attacks; furthermore, while entirely machine learning (ML)-based solutions are available with premier accuracy performance, they also require immense latency and do not guarantee operation in resource-constrained networks. In response to this impasse, we propose a novel, lightweight hybrid DDoS discovery framework that combines a machine learning classifier with adaptive threshold heuristics. We will employ a Logistic Regression model, chosen for its fidelity to predictive performance, along with its ability to relate each feature of the model. We trained the Logistic Regression model with traffic features, which, with the help of network tools, computes packet rate, byte rate, distribution of protocols, and the entropy of TCP flags. This ML model is integrated with a dynamic thresholding mechanism that will send alerts as soon as flood traffic is detected, allowing for near real time responses. The system has been developed in a modular software architecture that combines Scapy for packet processing with a Flask based web interface for visualization and monitoring in real time. We showed extensive evaluation with a custom testbed that simulates a baseline traffic load and several various types of DDoS attack vectors (SYN, UDP, ICMP floods), our hybrid approach achieved an detection accuracy of 95.2 %, precision of 94.8%, recall of 95.5%, and a false positive rate of only 3.9%. Importantly, the threshold heuristic effectively provides initial detection latencies of less than 200ms; the ML classification works in periodic batches every 50 ms. This combination of methods produced a better trade-off between speed, and accuracy, than any of the methods deployed separately. The system's low computational footprint makes it especially suitable for use in small-to-medium enterprises, academic testbeds, and as a peripheral monitoring module in Software-Defined Networking (SDN) environments. We conclude by outlining a future roadmap that includes integrating federated learning to ensure privacy, blockchain for immutable audit logs, and lightweight deep learning models (e.g., Quantized CNNs) for edge-leveraging.

An intrusion detection system (IDS) is an essential component of any modern network. The purpose of an IDS is to detect intrusion and generate appropriate alarms so that the intrusion can be mitigated. Implementing an IDS in a Software Defined Network (SDN) is easier since an SDN controller has a centralized view of the whole network. Researchers have made many efforts to use machine learning (ML) for developing network-based IDS in SDN. The network-based IDS analyzes different characteristics of incoming network traffic to detect intrusion. Early detection of intrusion is crucial for an IDS because if the intrusion is not detected quickly enough, it can cause severe damage, such as data breaches and service shutdowns. This paper focuses on detecting intrusion in SDN as early as possible using real-time flow-based features. Our aim is to detect intrusion with less amount of packets per flow, which not only facilitates early intrusion detection but also is useful when an intrusion flow has less number of packets. We show that although ML models perform well in offline training on a dataset, their performance decreases ~25% when fewer packets are used to generate features for the ML model. In all our experiments, a simple Random Forest (RF) algorithm outperforms a complex deep learning model on a publicly available dataset for intrusion detection in SDN.

The complexity of handling modern apps is causing older network architectures to struggle. As a result, Software Defined Networking (SDN) has developed into a paradigm-shifting network framework that enables administrators to exercise programmable control over whole network infrastructures. This development makes it easier to configure and operate large networks, but it also adds vulnerabilities, including the possibility of Distributed Denial of Service (DDoS) assaults that could take down the SDN controller. Integrating security tools like firewalls, intrusion detection and prevention systems, and anti-DDoS solutions is crucial to reducing this danger. In the context of SDN, leveraging the analytical power of Machine Learning (ML) algorithms to analyse network traffic patterns is a key tactic for fending off DDoS attacks. Effective defence systems are supported by these ML models, which can distinguish between normal network behaviour and DDoS assault traffic with ease. Decision trees (DT), support vector machines (SVM), and artificial neural networks (ANN) are examples of supervised ML techniques that have evolved into crucial tools in this field. These algorithms are developed utilising datasets with annotations that include examples of both legitimate and malicious network traffic. Once trained, the models may be used to instantly categorise incoming traffic, making it easier to identify and contain any DDoS attacks in real-time.

A DDoS attack detection and defense scheme using time-series analysis for SDN

The substantial growth of Internet-connected devices within the Internet of Things (IoT) has given rise to significant security challenges. Among the various threats confronting these interconnected devices, Denial of Service (DoS)/Distributed Denial of Service (DDoS) attacks emerge as significant concerns. The attacks, which seek to disrupt IoT services by flooding networks with unnecessary traffic, there is a critical need for robust security measures. Intrusion Detection Systems (IDS) are vital in identifying suspicious activities, yet many existing systems lack real-time capabilities to address evolving attack strategies. This study investigates the vulnerabilities of IoT networks and the pressing need to detect and classify DoS/DDoS attacks in real time. Traditional IDS, while effective in recognizing known attack patterns, fall short in identifying new attack types due to their reliance on historical data. To bridge this gap, this research focuses on developing an enhanced hybrid network intrusion detection and classification system. This study seeks to make contribution to the advancement of resilient security measures within IoT environments. The framework uses the Kth Nearest Neighbor (KNN) algorithm and dense neural networks to efficiently detect and categorize DoS/DDoS attacks in real time. To achieve this, a simulation model implementing the proposed hybrid algorithm will be developed. The framework utilized the MQTT-IoT-IDS2020 dataset, and a comparison was presented with recent approaches found in the literature. The results demonstrated enhanced performance in terms of true positive rate, accuracy, speed of detection.

Background & Objective: Detecting and mitigating Distributed Denial of Service (DDoS) attacks is a serious problem. In addition, new features and network deployments such as Software- Defined Networking (SDN) may open the door for new threats that did not previously exist. : Recent publications and patent are reviewed to find new techniques developed for integrating different mechanisms to secure networks against DDoS. Methods: This work presents a simple model for integrating different mechanisms to secure both SDN and legacy network in a hybrid cloud environment, it is called FocusON. It aims at mitigating DDoS attacks of a victim network. In addition, separating network monitoring from its control aims at mitigating DDoS attacks of a victim network. Traffic pattern analysis is apart from attack detection mechanism that gives a conceptual representation of a specific kind of DDoS attacks. DDoS detection is a completely automated process. Once called, for the reaction, the active response will be taken against the real IP source of the attacker. : The communication time overhead was tested in order to evaluate the remote server response time in case of deploying our proposed model mechanisms and without our proposed model. : Here we introduce a response mechanism that consists of an analysis of event logs, traffic patterns, and IP traceback. The proposed model categorizes the underlying network according to the location into a victim network and the source of attack (public cloud). Results & Conclusion:: The proposed model implemented in a hybrid cloud environment using the network of SDN and legacy network. The experimental setup was built using our network lab connected to the Amazon public cloud.

The increasing complexity and connectivity of networks lead to new and challenging vulnerabilities to be addressed for network security. As networks expand and diverse networks become interrelated, attackers leverage the broad scope of the global Internet to perpetrate large-scale attacks. Cloud environments, which are widely adopted, are fundamentally provisioned via the Internet bringing new challenges regarding security and privacy. However, network programmability and emerging technologies such as software-defined networking (SDN) and network functions virtualization (NFV) can advance techniques for intrusion detection and protection. In this chapter, we review the state of the art in scalable and collaborative intrusion detection systems (IDSs). Combining data plane programming with control level collaboration, we propose a model to simplify the detection of large-scale, distributed network attacks. This model simultaneously reduces the system overhead through direct mitigation at the network edge and enriches the detection process with corroboration of evidence from distributed sources.

Software Defined Network (SDN) is a new network construction. But due to its construction, SDN is vulnerable to be attacked by Distributed Denial of Service (DDoS) attack. So it is important to detect DDoS attack in SDN network. This paper presents a DDoS detection scheme based on k-means algorithm in SDN environment. The establishment of this scheme is based on the two hypotheses that the daily network works normally most of the time, and there is a significant difference between the data characteristics of normal situation and abnormal situation. At the same time, these two hypotheses are also true to the daily network condition. After demonstrating the validity of k-means clustering algorithm, the paper proposes 5 flow table features that can be used to detect DDoS attacks. Finally, the DDoS detection scheme was tested by simulation experiment. The test results showed that the method proposed by the author could effectively detect DDoS, with an average success rate of 97.78%.

Distributed denial of service (DDoS) attacks pose a significant security risk, particularly with the increasing reliance on cloud computing and information technology (IT). These attacks not only allow unauthorized users to access services but also deny legitimate users the ability to utilize them. Traditional antivirus solutions and firewalls prove insufficient in detecting DDoS attacks within large networks. Intrusion detection systems (IDS) are essential for detecting unauthorized or malicious activities and ensuring the confidentiality, integrity, and availability of services. However, traditional IDS often rely on predefined signatures and patterns, making them susceptible to evasion tactics. In response, this research introduces a deep learning (DL)-based IDS that integrates convolutional neural networks (CNN) with principal component analysis (PCA) and explores the application of vision transformers (ViT). The proposed hybrid model was tested on the CICDDoS2019 dataset, achieving a notable improvement in detection accuracy. Specifically, the CNN-based model initially identified DDoS attacks with an accuracy of 99.72%. Upon integrating ViT, the model’s accuracy further improved to 99.99%. This innovative approach signifies a considerable advancement in the detection capabilities for DDoS attacks and underscores the potential for integrating more sophisticated DL models into cybersecurity defenses.

Internet always remains the target for the cyberattacks, and attackers are getting equipped with more potent tools due to the advancement of technology to preach the security of the Internet. Industries and organizations are sponsoring many projects to avoid these kinds of problems. As a result, SDN (Software Defined Network) architecture is becoming an acceptable alternative for the traditional IP based networks which seems a better approach to defend the Internet. However, SDN is also vulnerable to many new threats because of its architectural concept. SDN might be a primary target for DoS (Denial of Service) and DDoS (Distributed Denial of Service) attacks due to centralized control and linking of data plane and control plane. In this paper, the we propose a novel technique for detection of DDoS attacks using information theory metric. We compared our approach with widely used Intrusion Detection Systems (IDSs) based on Shannon entropy and Renyi entropy, and proved that our proposed methodology has more power to detect malicious flows in SDN based networks. We have used precision, detection rate and FPR (False Positive Rate) as performance parameters for comparison, and validated the methodology using a topology implemented in Mininet network emulator.

Software-Defined Networks (SDN) provides more control and network operation over a network infrastructure as an emerging and revolutionary paradigm in networking. Operating the many network applications and preserving the network services and functions, the SDN controller is regarded as the operating system of the SDN-based network architecture. The SDN has several security problems because of its intricate design, even with all its amazing features. Denial-of-service (DoS) attacks continuously impact users and Internet service providers (ISPs). Because of its centralized design, distributed denial of service (DDoS) attacks on SDN are frequent and may have a widespread effect on the network, particularly at the control layer. We propose to implement both MLP (Multilayer Perceptron) and CNN (Convolutional Neural Networks) based on conventional methods to detect the Denial of Services (DDoS) attack. These models have got a complex optimizer installed on them to decrease the false positive or DDoS case detection efficiency. We use the SHAP feature selection technique to improve the detection procedure. By assisting in the identification of which features are most essential to spot the incidents, the approach aids in the process of enhancing precision and flammability. Fine-tuning the hyperparameters with the help of Bayesian optimization to obtain the best model performance is another important thing that we do in our model. Two datasets, InSDN and CICDDoS-2019, are utilized to assess the effectiveness of the proposed method, 99.95% for the true positive (TP) of the CICDDoS-2019 dataset and 99.98% for the InSDN dataset, the results show that the model is highly accurate.