Pradeepa Murugesan’s Post

Excited to share my latest publication in the International Journal of Scientific Research in Engineering and Management (IJSREM)! 🎉 📄 Title: Phishing Website Detection Using Machine Learning In this study, we developed a method to detect phishing websites using machine learning. By analyzing URL features like length, special characters, subdomains, and keywords, we built a model that accurately identifies phishing URLs. This research highlights the methodology and the model's performance in real-world scenarios. Grateful for the support and guidance from my mentor, Ms. Gayathri N, and collaborators, Pradeepa Murugesan and Janani Dhandayutham. 📖 Read the full paper here: https://lnkd.in/g-XMciH2 ISSN: 2582-3930 Impact Factor: 8.448 Volume 8 - Issue 07 July, 2024 #Research #Engineering #AI #MachineLearning #CyberSecurity #IJSREM #Publication #ScientificResearch

I'm excited to share that our paper, "STFL: Utilizing a Semi-Supervised, Transfer-Learning, Federated-Learning Approach to Detect Phishing URL Attacks" has been accepted for presentation at the International Joint Conference on Neural Networks (IJCNN) as part of IEEE WCCI, to be held at Pacifico Yokohama, Japan 🇯🇵, from June 30 to July 5, 2024. In this paper, we present a novel machine learning approach for phishing detection that combines semi-supervised learning, transfer learning, and federated learning. We train a Bi-LSTM autoencoder across decentralized edge devices containing unlabeled data. A centralized server collects the Bi-LSTM autoencoders and aggregates them into a global network using the FedAVG algorithm. The server then performs transfer learning to utilize the learned patterns from the global Bi-LSTM autoencoder networks and induce a classification model. Our experiments demonstrate that our proposed approach outperforms existing methods. I would like to thank all co-authors Prof. Yuval Elovici , Prof. Asaf Shabtai and Dr. Edita Grolman, for their help and guidance. Looking forward to presenting our paper at the conference. #IJCNN2024 #IEEEWCCI #DataScience #MachineLearning #CyberSecurity #FederatedLearning

🚨 Excited to Share My Latest Research on Malware Detection! 🚨 As part of my ongoing efforts in the field of cybersecurity, I’ve recently completed research on developing a PE file malware detection system using advanced deep learning techniques like Stacked CNN and RNN (LSTM, GRU) models. 🧠💻 🔍 Key Highlights of the Research: • Leveraged opcode frequency-based static analysis to detect malware in Windows PE files, a format responsible for ~89% of malicious files. • Explored multiple datasets, including the BODMAS dataset (57,293 malware & 77,142 benign samples) and DikeDataset, for a comparative analysis. • Achieved significant improvements in detection accuracy by combining CNNs for static pattern recognition and RNNs for sequential behavior analysis. • Highlighted the importance of model adaptability and optimization, with key findings showing that different architectures perform better depending on the dataset and task. 🔐 With the rising complexity of malware attacks, this research aims to contribute towards more robust detection systems that can adapt to evolving threats, leveraging deep learning to enhance cybersecurity defenses. I’m excited about the potential applications of this work and look forward to exploring future innovations in this field! Thank you to everyone who supported me throughout this journey, especially Prof. Rashmi Rane mam. Feel free to reach out if you’re interested in discussing this further! 💬 #Cybersecurity #MalwareDetection #DeepLearning #RNN #CNN #AI #MachineLearning #Research #BODMAS #DikeDataset #WindowsPE #CyberThreats #TechInnovation

🚀 Advancing Machine Learning Security Against Cyber Attacks in my Research work🔐 As a Machine Learning Research Assistant at the University of Houston, I’ve been working on a project titled “Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks.” In this work, I’ve successfully developed and implemented several advanced attack methods, including Boundary Attack, Square Attack, NES Attack, QEBA Attack, HSJA Attack, and Surfree Attack on CIFAR10 and ImageNet datasets. Using the ResNet152 model, I evaluated the impact of these attacks on adversarial images. 💻📊 These types of cyber attacks are frequently employed by malicious actors, making it essential to study their effects on machine learning models. I collected top 2 logits and Margin Loss from each adversarial image to perform statistical analysis and visualization, uncovering patterns and performance insights across all 6 attacks. 📈 🔍 This analysis will lay the foundation for developing robust defense mechanisms against these attacks, and I’m excited about what’s to come! 💪🤖 You can read more on this topic in the paper: https://lnkd.in/gfr_tNBd 🔗 #MachineLearning #Cybersecurity #BlackboxAttacks #AI #AdversarialAttacks #Research #DataScience #ResNet #ImageClassification #DefenseMechanisms

📢 Call for Chapters! Join us in shaping the upcoming book, Adversarial Example Detection, and Mitigation Using Machine Learning, part of the esteemed Advances in Information Security series by Springer! This is a unique opportunity to contribute your expertise to pioneering work in adversarial machine learning, sharing insights, methodologies, and advances with a global audience. Through this collaborative effort, you’ll help set a new standard in understanding and countering adversarial threats, pushing the field forward and inspiring future research. We’re calling on experts in cybersecurity, machine learning, and artificial intelligence to bring fresh perspectives and solutions to this critical topic. Let’s build a definitive resource together. Submit your chapter and become part of this transformative project! 🔗 More Information: https://lnkd.in/eHxAaYpH Editors: Dr. Rahim Taheri, Dr. Ehsan Nowroozi, and Prof. Lucas Cordeiro #CallForChapters #MachineLearning #AdversarialExamples #Cybersecurity #ArtificialIntelligence #InformationSecurity #SpringerBook #ResearchCollaboration #AcademicPublishing #InnovationInSecurity #MLforSecurity #AIResearch #DataScience University of Portsmouth Ravensbourne University London The University of Manchester IEEE IEEE Computer Society #AI #cybersecurity

Today's highlight is Shoshana Sugerman! If the RCC had a lead researcher position, it would definitely be Shoshana. She is always working on two or three different high-impact #research projects at the same time. Whether it's #quantum machine learning, exploring the ethics of Generative #AI on human-facing #cybersecurity tasks, and now evaluating compiler-based mitigation techniques, she is always excited to be contributing to the expansion of the state-of-the-art in cybersecurity knowledge. #security #cybersec #infosec #informationsecurity #generativeai #ml #machinelearning #RPI Rensselaer Polytechnic Institute Rensselaer Polytechnic Institute Information Technology & Web Science

🌟 Exciting News! 🌟 I'm thrilled to share that our paper titled "MACHINE LEARNING-BASED STRATEGIES FOR DETECTING CYBERBULLYING IN ONLINE CHATS" has been officially published in the International Journal of Innovative Science and Research Technology - IJISRT (Digital Library). You can read the full paper here: https://lnkd.in/d9T8u5x6 A big thank you to everyone who supported this work especially my supervisor Fati Oiza Salami. This publication marks a significant milestone in our efforts to leverage machine learning for creating safer online environments. Feel free to reach out if you have any questions or would like to discuss the research further! #MachineLearning #Cyberbullying #Research #Publication #Cybersecurity #AI

We are pleased to announce that our recent research paper has been accepted for presentation at the 2024 IEEE International Conference on Cyber Security and Resilience (#IoSec2024), to be held in London. The paper, titled "#Verifying the #Robustness of Machine Learning-based #Intrusion #Detection Against Adversarial Perturbation," is authored by Rahim Taheri, Mehrdad Hajizadeh, and Prof. Thomas Bauschert. This research is particularly interesting as it explores innovative methods for formally #verifying the security and robustness of neural networks in intrusion detection systems. This study addresses the significant vulnerabilities faced by neural networks (NNs) in various security tasks, including spam detection, phishing, and intrusion detection systems (#IDS). Adversarial attacks exploit the #fragilities within machine-learning models, posing a considerable threat. Our study introduces a #novel approach to formally verify and enhance the resilience of both shallow and deep NN-based Intrusion Detection. We investigated the effectiveness of various #activationfunctions using benchmark IDS datasets (e.g. #CICIDS2017 and #UNSWNB15). Our findings indicate that ReLU and Leaky-ReLU functions enhance resistance in shallow networks, whereas Tanh functions perform better in deep networks. This study provides certified accuracies for models subjected to various input #perturbations ranging from 0.0001 to 0.9, marking a significant advancement in verifying the #security of NNs. #CyberSecurity #MachineLearning #NeuralNetworks #IntrusionDetection #AdversarialAttacks #Research #TechConference #IEEE2024 #AI #DeepLearning #CyberResilience #NetworkSecurity #MLSecurity #TechInnovation #AIResearch #CyberDefense #CyberThreats #SecurityResearch #IBP #Verification #TechNews #ResearchPaper #AcademicResearch #IEEECSR Ehsan Nowroozi Ravensbourne University London #IEEE

🚀 Just wrapped up an incredible week at Black Hat 2024! 🌟 The experience was nothing short of amazing, especially completing the Black Hat Machine Learning course. Diving deep into the world of ML, we explored its rapid advancements and the security challenges that come with them. From hands-on labs in Jupyter notebooks to understanding adversarial techniques, this course provided invaluable insights into assessing and securing ML systems. 🛡️💻 A huge thank you to the instructors (Will Pearce Rich Harang Becca Lynch Erick Galinkin) and Elle S. for giving me the opportunity to participate in an engaging and enlightening experience. Looking forward to applying these new skills to tackle emerging security threats in the AI landscape! 🤖🔍 #BlackHat2024 #MachineLearning #CyberSecurity #AI #ML #Training #ProfessionalGrowth

#JCP #article #MostView [Most Viewed Paper] 🔔 Title: Comparison of Deepfake Detection Techniques through Deep Learning by Maryam Taeb, and Chi Hongmei from FAMU-FSU College of Engineering, and Florida A&M University See more details at 👉 : https://lnkd.in/gtHkZbwj #CyberSecurity #deepfakedetection #digitalforensics #mediaforensics #deeplearning #VGG19 #manipulation