Project Abstract

In the current digital age, the rapid escalation of spam has necessitated robust countermeasures. This project was initiated in response to this critical challenge, aiming to develop an advanced spam identification system that leverages machine learning (ML) and homomorphic encryption (HE). These technologies not only enhance spam detection capabilities but also ensure the privacy and security of user data, a vital concern in today?��s digital communication networks.The research uniquely positions itself by integrating ML with HE to analyze encrypted data without decryption, addressing privacy concerns while maintaining efficient spam detection. The main aim is to create a system capable of adapting to evolving spam tactics without compromising data privacy, setting a new standard in the field.Methodologically, the project employs a hybrid approach combining classical ML algorithms with advanced cryptographic techniques. The proposed models, such as Naive Bayes and neural networks, are evaluated for their effectiveness in spam detection across varied and evolving scenarios. This approach not only aims to enhance accuracy but also focuses on maintaining the usability and security of the data during processing.While the project is ongoing, the expected findings include the development of a scalable and adaptive spam detection system that significantly reduces false positives and adapts to new spam tactics. This system is anticipated to provide deep insights into the integration of ML and HE, showcasing a significant advancement in privacy-preserving technologies.Upon successful completion, this research will contribute substantially to the fields of cybersecurity and digital communication. It will demonstrate a novel application of HE in real-world scenarios, providing a blueprint for future technologies that require robust data security measures without sacrificing functionality. This project is poised to set a benchmark in the integration of machine learning with advanced encryption technologies, offering significant implications for both academic research and practical applications in spam detection.

Keywords: Machine Learning and Homomorphic Encryption Integration, Privacy-Preserving Spam Detection, Adaptive Spam Identification

 Conference Details

Session: Presentation Stream 10 at Presentation Slot 8

Location: CoFo 002 at Tuesday 7th 13:30 – 17:00

Markers: Randell Gaya, George Brooks (GTA)

Course: MSc Advanced Computer Science, Masters PG

Future Plans: I’m looking for work