CyberSecDome - EU project’s Post

Thrilled to announce our paper, "𝐌𝐚𝐜𝐡𝐢𝐧𝐞 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠-𝐁𝐚𝐬𝐞𝐝 𝐃𝐞𝐭𝐞𝐜𝐭𝐢𝐨𝐧 𝐨𝐟 𝐃𝐃𝐨𝐒 𝐀𝐭𝐭𝐚𝐜𝐤𝐬 𝐨𝐧 𝐈𝐨𝐓 𝐃𝐞𝐯𝐢𝐜𝐞𝐬 𝐢𝐧 𝐌𝐮𝐥𝐭𝐢-𝐄𝐧𝐞𝐫𝐠𝐲 𝐒𝐲𝐬𝐭𝐞𝐦𝐬," is accepted for publication in the Egyptian Informatics Journal, a 𝐐1 journal with an 𝐈𝐅 𝐨𝐟 5! https://lnkd.in/d2AJKs-e Our study addresses the growing cybersecurity threats, particularly DDoS attacks on Energy Hubs (EH) through IoT devices, by evaluating supervised machine learning algorithms. Using the CICDDOS2019 and KDD-CUP datasets, models like Gradient Boosting, Decision Tree, and SVM were analyzed. Gradient Boosting proved to be the most effective model for predicting DDoS attacks. Hybrid models combining Gradient Boosting with SVM or Decision Tree also performed well but with varied precision and recall, emphasizing the need for tailored ML approaches to strengthen EH system security. I would like to express my sincere gratitude to the authors for their invaluable contributions.

Excited to share that our paper titled "Robust Botnet Detection Approach for Known and Unknown Attacks in IoT Networks Using Stacked Multi-classifier and Adaptive Thresholding" has been published in the Arabian Journal for Science and Engineering, Springer ( Scopus and SCIE Indexed I.F 2.9).This work, presents a cutting-edge method for detecting botnet activity in IoT networks. By leveraging a stacked multi-classifier and adaptive thresholding, we achieve robust detection capabilities against both known and unknown attacks, enhancing the security of IoT ecosystems. Our research contributes to the advancement of cybersecurity in IoT, offering practical solutions for real-world threats. Special thanks to the Editorial team for their dedication and to the Arabian Journal of Science and Engineering for this valuable publication opportunity. Looking forward to more collaborations and innovations in the field! #IoTSecurity #BotnetDetection #Cybersecurity #ResearchPublication #ArabianJournalforScienceandEngineering #ScopusIndexed #SCIEIndexed. The research paper can be read at https://lnkd.in/dtiBiS4B

📢 Exciting Read on IoT Security! I'm thrilled to share a comprehensive survey paper on "Securing Internet of Things Using Machine and Deep Learning Methods" 🔍 Highlights: - Overview of IoT architecture and its exponential growth. - Discussion on security challenges and vulnerabilities in IoT systems. - In-depth review of how machine learning (ML) and deep learning (DL) techniques are revolutionizing IoT security. - Analysis of recent studies and future research directions to enhance IoT security. This paper is a must-read for anyone interested in IoT, cybersecurity, and the application of advanced ML/DL techniques. A special thanks to my professor Hassan Badir for sharing this insightful paper with us 🙏 #IoT #Cybersecurity #MachineLearning #DeepLearning #Research #TechInnovation

🚨 New Paper 🚨 We are proud to announce that our new open-access article "Benchmarking of Secure Group Communication schemes with focus on IoT" has been published in Springer's "Discover Data" journal as part of the "Data Privacy Protection in IoT Communication" collection. Link: https://lnkd.in/eWUMP-BZ Abstract: As Internet of Things (IoT) devices become ubiquitous, they face increasing cybersecurity threats. Unlike standard 1-to-1 communication, the unique challenge posed by n-to-n communication in IoT is that messages must not be encrypted for a single recipient but for a group of recipients. For this reason, using Secure Group Communication (SGC) schemes is necessary to encrypt n-to-n communication efficiently for large group sizes. To this end, the literature presents various SGC schemes with varying features, performance profiles, and architectures, making the selection process challenging. A selection from this multitude of SGC schemes should best be made based on a benchmark that provides an overview of the performance of the schemes. Such a benchmark would make it much easier for developers to select an SGC scheme, but such a benchmark still needs to be created. This paper aims to close this gap by presenting a benchmark for SGC schemes that focus on IoT. Since the design of a benchmark first requires the definition of the underlying business problems, we defined suitable problems for using SGC schemes in the IoT sector as the first step. We identified a common problem for the centralized and decentralized/hybrid SGC schemes, whereas the distributed/contributory SGC schemes required defining an independent business problem. Based on these business problems, we first designed a specification-based benchmark, which we then extended to a hybrid benchmark through corresponding implementations. Finally, we deployed our hybrid benchmark in a typical IoT environment and measured and compared the performance of different SGC schemes. Our findings reveal notable impacts on calculation times and storage requirements without a trusted Central Instance (CI) in distributed/contributory SGC schemes.

I'm thrilled to share that my chapter, "Challenges, Existing Strategies, and New Barriers in IoT Vulnerability Assessment for Sustainable Computing," has been published in the book "Big Data and Edge Intelligence for Enhanced Cyber Defense." This work delves into the evolving landscape of IoT security, exploring current strategies and the emerging challenges we face in achieving sustainable and secure computing environments. It's an honor to contribute to a field that is so crucial for our digital future. A big thank you to Dr. Delshi R. who supported me throughout this journey. I hope this chapter provides valuable insights and sparks further discussion and innovation in cyber defense. #IoT #CyberSecurity #BigData #EdgeIntelligence #SustainableComputing #Research #Publication

Are you interested in implementing a digital twin? Dave Cleminson - GAICD MDS will be speaking on 'Living digital twins: it's all about the data'. It’s definitely going to be a dynamic discussion on how digital twins can be the ultimate digital realisation of any physical object or operational system - but the real value hinges on the data input and on the intelligence applied to the output. You can still secure your spot here 👉 https://lnkd.in/g8KZYxH #conferences2024 #data #naturepositivity #iot #iotimpact #iotallianceaustralia

I'm thrilled to my 5th contribution to a new research paper, which delves into the intersection of Artificial Intelligence, Cybersecurity, Deep Learning, Federated Learning, and the Internet of Things (IoT). In this paper, we address a pressing concern: the security of IoT devices. With the rapid proliferation of these interconnected systems, cyberattacks have emerged as significant threats to individuals and organizations alike. Traditional centralized security methods are becoming increasingly inadequate due to the vast amounts of data generated by numerous devices. Our research explores how Federated Learning (FL) can offer a robust solution to mitigate privacy issues associated with centralized approaches while enhancing cybersecurity in IoT applications. By leveraging FL and deep learning techniques, we propose a federated approach that forms a collaborative network of models among various participants. Key highlights from our study include: * Utilization of the Inception Time and Multi-Head Attention CNN algorithms based on FL to effectively detect cyber-attacks. * Analysis of data privacy under two distribution modes: IID and Non-IID. * Comparison with FedAvg and FedMA algorithms to aggregate local model updates. * Demonstrated results show that our federated inception model achieved impressive global accuracies of 93.91% and 93.49% using Multi-Head Attention. https://lnkd.in/dGa6yd5z #AI #Cybersecurity #DeepLearning #FederatedLearning #IoT

Excited to share my third contribution to a new research paper on enhancing IoT security through parallel machine learning! With the rapid growth of IoT devices, safeguarding sensitive data has become paramount. Our research focused on developing a robust system to detect and predict cyberattacks using advanced ML techniques. By parallelizing the training process, we achieved impressive results in terms of accuracy and speed. This collaboration has been an incredible learning experience, and I'm proud to be part of a team driving innovation in cybersecurity. https://lnkd.in/dhbtcZCn #IoT #cybersecurity #machinelearning #AI #research #datascience #opendata #parallel

🚀 Exciting Announcement: The GREENEDGE Challenge is open!!!🚀    A DATA challenge is launched within the GREENDGE action.   It features three possible lines of work: 1) Cybersecurity: “Cyber Threats Detection through Network Energy Consumption Analysis”  2) Image Classification: “Energy Aware Image Classification”   3) Internet of Things: “Energy Efficient IoT Networks”. The lines deal with topics related to the GREENEDGE core mission, that is, to devise energy-efficient tools for computing in networks. 🌱 BS, MS level and PhD students are invited to participate in the challenge. The submitted projects will undergo an evaluation by a team of scientists from the GREENEDGE consortium. The winners will be invited to participate in the final GREENEDGE workshop where they will present their work and will receive a prize. The final workshop will be co-located with an international conference and will take place around September 2024 (detailed instructions will follow).    Subscription deadline: May 15, 2024. ⏰   All the details are available in GREENEDGE website: https://lnkd.in/gZcQUrQm #msca #ai #edgecompting #sustainability #research #phd #challenge #contest #cybersecurity #imageclassification #iot #forourplanet

📣 Maybe of interest for bachelor, master and PhD students working in the areas of #machinelearning, #iot, #cybersecurity, #energyefficiency. 💡Three challenging problem statements have been proposed by our Greenedge ITN early-stage researchers and are waiting for your solutions. 👉 Registrations are already open! #phd #challenge #data #award