PhD Thesis on Intrusion Detection System

Intrusion Detection System (IDS) research topic is now one of the trending topics to detect malicious or unauthorized access in a computer network. It is one of the tools for security to identify the unwanted or suspicious activities in the system. Here in this research we propose IDS to overcome the existing issues:

  1. Define Intrusion Detection System

Initially we begin with the definition of IDS. It will be a software application or device.  It is a network protection tool which tracks the network traffic and the devices for policy offenses, harmful activity or unauthorized activity. It identifies the harmful activity and then creates an alarm when they must be identified. On the basis of these alarms, a Security Operations Center (SOC) incident responder or predictor examines the problem and takes the corresponding actions to rectify the danger.

  1. What is Intrusion Detection System?

Afterwards we look over the descriptive explanations of this proposed IDS technique. It is a protective tool which is created to track or trace the activities of the system or network to identify the unauthorized or harmful manner. It serves as an investigation system, regularly identifies the incoming activity of the system or network traffic and searches for the signs of possible protection breaches, policy offenses or attacks.

  1. Where Intrusion Detection System used?

Next to the descriptive explanation we discuss where to use this proposed technology. It is widely employed in different environments where the identification of suspicious or harmful activities is crucial for handling protection. Several common applications are cloud infrastructure, enterprise networks, online services, critical infrastructure, data centers, industrial control systems and government networks.

  1. Why Intrusion Detection System technology proposed? , previous technology issues

Here we discuss why our proposed IDS technology is proposed and some of its existing technology issues. This study establishes the hybrid IDS technology which joins the blockchain techniques and anomaly detection; particularly it is created for 6G IoT environments. The scope contains executing, calculating and improving the systems performance to enhance IoT network protection on inconsistent cyber-attacks. The major struggle is to build a system which performs this effectively to identify and utilize a hybrid IDS system created to tackle the specific challenges and characters of IoT environments. Some of the issues that exists in the previous technologies are increased computational overhead, increased complexity, Lack of security and lack of interoperability

  1. Algorithms / protocols

Several algorithms are used in our proposed research to find the accurate findings. The methods that we used are Distributed Hash Table (DHT), Modified Density Peak Clustering with the Capuchin Search Algorithm (MDPC-CapSA) and Deep Convolutional Generative Adversarial network with a Capuchin Search Algorithm (MDPC-CapSA).

  1. Comparative study / Analysis

We propose a novel technology that has many features as compared to the previous methods. Several methods that we utilized for this research are as follow:

  • To avoid the harmful access to the digital systems or services, the user’s identification is first confirmed through the user authentication procedure. To safeguard the digital assaults, private data and make sure the protective user authentication, the combination of internet sites and systems is essential for this research.
  • This research also displays how clustering nodes will decrease cyber-attacks and handle the reliability of the network communications. This technique offers improved attack detection capacities in IDS by employing MDPC-CapSA.
  • We integrate DCGAN-OC-SVM for 6G-IoT anomaly identification and gateway collaboration in the IDS. This distinct method makes sure effective network protection and threat identification while also improving the future security for hyper-linked 6G IoT environments.
  • By combining DHT with blockchain technique to estimate the problems in protection and to enhance the data quality to make sure protective smart contracts, data storage, secure records for access control safety of private data.
  1. Simulation results / Parameters

Our proposed IDS technique is to enhance the security for threat identification in this research. Here we compare several performance metrics to obtain the best findings. The methods that we compared are Detection rate, Accuracy, Scalability, Recall, False alarm rate, Precision and F1 Score with the Number of users.

  1. Dataset LINKS / Important URL

In this research we propose an IDS technique that is widely used in many places and it is proposed to overcome several previous technology issues with the help of below provided links:

  1. Intrusion Detection System Applications

Now we see the applications for IDS technology, it plays an important role in protecting the IoT applications because of the distinct difficulties and limitations essential in IoT environments. Some of the applications of IDS are Edge based IDS, Device level IDS, Behavioral analysis and anomaly detection, Network level IDS and Cloud based IDS.

  1. Topology for Intrusion Detection System

Let’s see the topology to be used for this IDS technique. A hybrid IDS for IoT consists of integrating the various kinds of intrusion detection system or technique to improve the whole protection of the IoT environments. While creating this topology for hybrid IDS for IoT, some of the factors that require to be considered, and this involves the distributed nature of IoT systems, the requirement for real-time detection and response and resource constraints of IoT devices.

  1. Environment for Intrusion Detection System

The environment for this proposed hybrid IDS in IoT requires to be precisely created to tackle the distinct difficulties and features of the IoT environment. Its environment must be created to conform to the diverse and shared nature of IoT deployments. The combination of different identification techniques, continuous consistency with IoT platforms and consideration of resource constraints are the main factors in constructing an efficient hybrid IDS for IoT security.

  1. Simulation tools

For this research the software requirements that require for this are listed below. The tool that is utilized to implement the research is NS 3.26. The work is executed by using the operating system Ubuntu- 14.04 LTS (32 bit). Then the processor here we used for this research is Intel(R) core™ i5 -4590S CPU@ 2.5 GHZ.

  1. Results

Intrusion Detection System is utilized to detect unauthorized or any criminal activities in the computer network. We proposed this to our research by overcoming the existing technology issues and to compare various metrics to obtain the best outcome. This research operated by using the system OS Ubuntu- 14.04 LTS (32 bit).

Intrusion Detection System Research Ideas:

Below, we provide the topics that are related to the IDS method that detects and analyzes unauthorized activity and to offer security. We utilize these topics when the doubts or clarifications arise among us:

  1. Research on the Application of Distributed Intrusion Detection System in Campus Network
  2. Intrusion Detection System using Ensemble based Feature Selection Technique
  3. Machine Learning-based Intrusion Detection System using Wireless Sensor Networks
  4. A Novel Ensemble based Model for Intrusion Detection System
  5. Intrusion Detection System in Wireless Sensor Networks using Modified Recurrent Neural Network with Long Short-Term Memory
  6. To Decrease the Rate of Cyber Anomalies Using Intrusion Detection System with Feature Selection Approach
  7. Intrusion Detection System in Mobile Cloud Computing Using Bat Optimization Algorithm-Support Vector Machine
  8. A Systematic Literature Review on Host-Based Intrusion Detection Systems
  9. Evaluating Security enhancement through Machine Learning Approaches for Anomaly Based Intrusion Detection Systems
  10. Performance Tradeoff in ML-Based Intrusion Detection Systems: Efficacy vs. Resource Usage
  11. Enhancing Security of Host-Based Intrusion Detection Systems for the Internet of Things
  12. A Study of AI-Based In-Vehicle Intrusion Detection Systems
  13. Network Intrusion Detection System Using Decision Tree and KNN Algorithm
  14. An AI-Driven Based Cybersecurity System for Network Intrusion Detection System in Hybrid with EPO and CNNet-LAM
  15. Deep Learning based Network based Intrusion Detection System in Industrial Internet of Things
  16. Detecting DDoS Attacks Through AI driven SDN Intrusion Detection System
  17. A Hybrid Framework for Effective Intrusion Detection System in Wireless Networks
  18. Enhanced Network Intrusion Detection System Using PCGSO-Optimized BI-GRU Model in AI-Driven Cybersecurity
  19. EESNN: Hybrid Deep Learning Empowered Spatial–Temporal Features for Network Intrusion Detection System
  20. Manticore: An Unsupervised Intrusion Detection System Based on Contrastive Learning in 5G Networks
  21. A Comprehensive Survey: Exploring Current Trends and Challenges in Intrusion Detection and Prevention Systems in the Cloud Computing Paradigm
  22. “A Comprehensive Review of Advanced Artificial Intelligence Techniques to Enhance Intrusion Detection Systems”
  23. Kalis2.0—A SECaaS-Based Context-Aware Self-Adaptive Intrusion Detection System for IoT
  24. Multi-Sensors Space and Time Dimension Based Intrusion Detection System in Automated Vehicles
  25. MLIDS: Revolutionizing of IoT based Digital Security Mechanism with Machine Learning Assisted Intrusion Detection System
  26. An Enhanced Intrusion Detection System Model Using Machine Learning Algorithm
  27. Improving the security of Internet of Things (IoT) using Intrusion Detection System(IDS)
  28. Explainable AI for Intrusion Detection Systems: LIME and SHAP Applicability on Multi-Layer Perceptron
  29. Development and implementation of a facial recognition intrusion detection system
  30. IdentifierIDS: A Practical Voltage-Based Intrusion Detection System for Real In-Vehicle Networks
  31. Intrusion Detection System for MIL-STD-1553 Based on Convolutional Neural Networks With Binary Images and Adaptive Quantization
  32. An Improved Intrusion Detection system for securing academic information on the cloud using a blockchain-based security framework
  33. CVMIDS: Cloud–Vehicle Collaborative Intrusion Detection System for Internet of Vehicles
  34. A Hybrid System for Integrating Cross-Correlation, DNNs and LSTMs for Enhanced Intrusion Detection System
  35. A Collaborative Software Defined Network-Based Smart Grid Intrusion Detection System
  36. FL-IDS: Federated Learning-Based Intrusion Detection System Using Edge Devices for Transportation IoT
  37. A Novel Intrusion Detection System Based on Artificial Neural Network and Genetic Algorithm With a New Dimensionality Reduction Technique for UAV Communication
  38. X-CANIDS: Signal-Aware Explainable Intrusion Detection System for Controller Area Network-Based In-Vehicle Network
  39. A Signature-Based Wireless Intrusion Detection System Framework for Multi-Channel Man-in-the-Middle Attacks Against Protected Wi-Fi Networks
  40. Exploring Machine Learning’s Role in Intrusion Detection Systems for Network Security
  41. An Incremental Majority Voting Approach for Intrusion Detection System Based on Machine Learning
  42. Intrusion Detection and Prevention System for Early Detection and Mitigation of DDoS Attacks in SDN Environment
  43. AIDPS: Adaptive Intrusion Detection and Prevention System for Underwater Acoustic Sensor Networks
  44. Quantum-Assisted Activation for Supervised Learning in Healthcare-Based Intrusion Detection Systems
  45. Heterogeneous Data-Aware Federated Learning for Intrusion Detection Systems via Meta-Sampling in Artificial Intelligence of Things
  46. Intrusion Detection Systems in Automotive Ethernet Networks: Challenges, Opportunities and Future Research Trends
  47. Automatic Evasion of Machine Learning-Based Network Intrusion Detection Systems
  48. Intrusion Detection System to detect impersonation attacks in IoT networks
  49. CF-AIDS: Comprehensive Frequency-Agnostic Intrusion Detection System on In-Vehicle Network
  50. Performance Analysis of Intrusion Detection System Using ML Techniques