IEEE 2023: Machine Learning and Software-Defined Networking to Detect DDoS Attacks in IOT Networks
Abstract: In an era marked by the rapid proliferation of IoT devices, safeguarding network security has become an imperative task. This interim report provides an overview of our ongoing project, "Empowering Cyber Defense: Machine Learning Algorithm for Attack Identification," aimed at enhancing intrusion detection in IoT environments. Leveraging the power of Artificial Neural Networks (ANN), SVM (Support Vector Machine), a system tackles the formidable challenge of identifying attacks in the NF-ToN-IoT-V2 dataset, Our research explores four key attack classifications: Benign, Scanning, Password-based, and DDoS attacks. Through rigorous experimentation, we assess the efficacy of our proposed model in accurately identifying these attacks. By harnessing the rich features of IoT network traffic data, our system demonstrates promising results in terms of precision, recall, and overall classification performance. This interim report provides insights into our methodology, dataset, and initial findings, underscoring the significance of our research in bolstering IoT network security and defending against evolving cyber threats. In this we achieved validation accuracy.
Abstract: Cyber-bullying is a form of cyber-aggression that has become a major concern in today’s information society. In the digital age, the Internet has enabled the circulation of ideas and information and, in turn, has increased awareness among people. However, this does not come with its drawbacks. With the proliferation of online platforms, hoaxers can easily lure people towards their propagandist views or false news. The need to root out such false information and hate speech during this COVID-19 pandemic has never been more essential. The following study presents a survey of various papers that attempt to tackle similar problem statements with fake news, sentiment classification, and topic extraction. The paper focuses on how existing quality research can help improve the current state of research on COVID-19 related datasets by guiding researchers towards valuable procedures to help governmental authorities combat the rise in the spread of false news and the malicious and hate comments.
Abstract: Integration of the Internet into the entities of the different domains of human society (such as smart homes, health care, smart grids, manufacturing processes, product supply chains, and environmental monitoring) is emerging as a new paradigm called the Internet of Things (IoT). However, the ubiquitous and wide-range IoT networks make them prone to cyber attacks. This research aims to investigate and mitigate the escalating threat of malware in Edge/Fog Computing environments, specifically originating from Internet of Things (IoT) devices. Leveraging the CICIDS 2017 dataset, we propose a two-fold approach employing Support Vector Machine (SVM) algorithm and a Hybrid Deep Learning model, combining Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) networks. The SVM algorithm will provide a robust baseline for detecting known malware patterns, while the CNN-LSTM hybrid model will enhance the system's capability to identify complex, evolving threats. Our study seeks to contribute to the development of advanced intrusion detection systems tailored for the unique challenges posed by Edge/Fog Computing, ensuring the security and integrity of IoT-driven ecosystems. The research outcomes are anticipated to shed light on effective strategies to safeguard critical infrastructures in the era of pervasive IoT adoption.
IEEE 2023: Phishing Web Sites Features Classification Based on Learning Machine.
Abstract: Phishing are one of the most common and most dangerous attacks among cybercrimes. The aim of these attacks is to steal the information used by individuals and organizations to conduct transactions. Phishing websites contain various hints among their contents and web browser-based information. Phishing is a new type of network attack where the attacker creates a replica of an existing Web page to fool users (e.g., by using specially designed e-mails or instant messages) into submitting personal, financial, or password data to what they think is their service provides' Web site. The purpose of this study is to perform Extreme Learning Machine (ELM) based classification for 30 features including Phishing Websites Data in UCI Machine Learning Repository database.
No comments:
Post a Comment