The Department of Computer Science and Engineering is proud to announce that Assistant Professors Dr Kshira Sagar Sahoo and Dr Tapas Kumar Mishra, along with their research scholar Ms Arati Behera, have published their paper “A Combination Learning Framework to Uncover Cyberattacks in IoT Networks” in the prestigious Q1 journal Internet of Things, which has an Impact factor of 6.

The article addresses IoT security challenges by utilising Software Defined Networking technology and AI. The authors use Genetic Algorithm to select the most important data features and a hybrid deep learning model combining CNN, Bi-GRU, and Bi-LSTM to detect cyber-attacks effectively. Tested on real-world IoT datasets, the system demonstrates superior accuracy, faster detection, and lower resource usage than existing methods, making it a promising solution for securing resource-constrained IoT networks.

Abstract

This study addresses the security challenges in IoT networks, focusing on resource constraints and vulnerabilities to cyber-attacks. Utilising Software Defined Networking and its adaptability, the authors propose an efficient security framework using a Genetic Algorithm for feature selection and Mutual Information (MI) for feature ranking. A hybrid Deep Neural Network (DNN) combining CNN, Bi-GRU, and Bi-LSTM is developed to detect attacks. Evaluated on InSDN, UNSW-NB15, and CICIoT 2023 datasets, the model outperforms existing methods in accuracy, detection time, MCC, and resource efficiency, demonstrating its potential as a scalable and effective solution for IoT network security.

Practical Implementation/ Social Implications of the Research

The practical implementation of this research lies in enhancing the security of IoT networks, which are increasingly integral to smart homes, healthcare, transportation, and industrial systems. By detecting and mitigating cyber-attacks efficiently, the proposed model can safeguard sensitive data, prevent service disruptions, and ensure the reliability of IoT systems.

Collaborations

This research has been conducted in partnership with Umea University Sweden.

Future Research Plans

There is potential to enhance the Deep Learning approach further to reduce the execution time at the power crunch device. Additionally, federated learning could be investigated as a use case, especially concerning edge devices within typical software-defined IoT networks.

Read more

Overall Architecture

Work Flow

Farming is often regarded as an occupation that is challenging and has become a sobriquet for hardship and unpredictability, leaving farmers financially vulnerable and many a times at the brink of poverty. Insuring crops can, however, minimise the risk of loss, making it a viable option as long as the process doesn’t get bogged down by excessive bureaucracy and cumbersome paperwork. Dr Naga Sravanthi Puppala, Assistant Professor at the Department of Computer Science and Engineering has come up with a game-changing solution of utilising blockchain technology and real time IoT data for automatic and quick coverage of crops by simplifying the insurance process thereby helping reshaping the future of agriculture, just when it’s needed most.

Abstract

The invention is a groundbreaking design patent that employs a single, sophisticated smart contract policy to autonomously manage the entire crop insurance process. This system innovatively combines blockchain technology with real-time IoT data collection to create an efficient, transparent, and reliable insurance solution for farmers. Central to this invention is a singular smart contract policy designed to oversee every stage of the insurance lifecycle, from policy issuance and dynamic risk assessment to claims processing and payout disbursement. This smart contract policy is meticulously programmed with specific conditions and thresholds, including weather patterns, soil moisture levels, and crop health indicators, all monitored by IoT devices in the field. As these conditions are tracked in real-time, the smart contract policy autonomously adjusts coverage and triggers payouts when necessary, eliminating the need for human intervention. This system not only enhances efficiency by reducing administrative costs but also ensures prompt and accurate payouts. By relying on tamper-proof data and predefined conditions, the invention offers a secure and transparent approach to crop insurance, providing farmers with a dependable safety net against crop losses.
In short, this invention makes crop insurance smarter, simpler, and fairer, giving farmers the support they need when they need it most.

Practical Implementation and Social Implications of the Research

Practical Implementation

• Blockchain: Secure platform for immutable records.
• Smart Contracts: Automate insurance claims based on predefined triggers.
• IoT Devices: Monitor crop and environmental data in real-time.
• Oracles: Fetch external data (e.g., weather reports).
• Workflow: Farmers enroll, pay premiums digitally, and receive automatic payouts if crop damage is detected.

Social Implications

• Transparency: Eliminates fraud and delays in claims.
• Inclusivity: Provides insurance access to small-scale farmers.
• Economic Stability: Reduces financial strain on farmers after disasters.
• Sustainability: Encourages data-driven, risk-resilient agriculture.

Future Research Plans:

Building upon the foundation of this invention, my future research will focus on advancing and expanding its applications to maximize impact in agriculture and beyond. Key areas of exploration include:

1. Enhancing IoT Integration for Precision Agriculture

Aimed to develop more advanced IoT devices and sensors that can collect highly specific data on soil quality, weather patterns, and crop health. This data will improve the system’s ability to predict risks and tailor insurance policies to individual farms. Research will also involve optimizing sensor networks for affordability and accessibility to smallholder farmers.

2. Developing Dynamic Risk Assessment Models

By incorporating machine learning and predictive analytics, I plan to create dynamic risk assessment models. These models will continuously learn from real-time data and historical trends, allowing the system to provide proactive alerts to farmers about potential risks and automatically adjust insurance terms to reflect current conditions.

3. Expanding Blockchain Applications Beyond Crop Insurance

While the current focus is on crop insurance, blockchain’s secure and transparent nature offers opportunities for broader agricultural applications. I intend to explore its use for supply chain traceability, ensuring that crops reach markets efficiently and without tampering, and for facilitating peer-to-peer lending among farmers.

4. Testing and Scaling in Diverse Agricultural Environments

Field trials will be conducted in various regions and farming contexts to test the system’s adaptability and scalability. This includes:

• Testing in regions prone to extreme weather conditions.
• Evaluating the system’s performance in specialized farming industries, such as vineyards or organic farming.
• Collaborating with agricultural cooperatives to implement the system across multiple farms simultaneously.

5. Social and Economic Impact Assessment

A critical part of my research will involve studying the socioeconomic impact of this invention on farmers, particularly smallholder farmers. I aim to assess how it influences their livelihoods, productivity, and financial security. This will guide future improvements to make the system more inclusive and equitable.

6. Exploring Policy and Regulatory Frameworks

For widespread adoption, I plan to engage with policymakers to align the system with existing agricultural and insurance regulations. The research will focus on creating policy frameworks that encourage adoption, particularly in developing regions and addressing potential legal challenges related to blockchain and data privacy.

7. Collaborating for Multi-Sectoral Impact

Partnerships with financial institutions, agritech companies, and government agencies to co-develop solutions that integrate blockchain-based insurance with other agricultural services, such as microloans, subsidies, and educational programs.

By addressing these areas, my research will contribute to creating a more resilient and sustainable agricultural ecosystem, empowering farmers with cutting-edge technology while enhancing food security and economic stability globally.