Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLM-RoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deepset in huggingface, and this fine-tuned model achieves impressive results with 99.13% accuracy, 100% precision, 98.33% recall and 99.15% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks.

The primary goal of authentic learning is to provide students with an engaging learning environment that offers hands-on experiences in solving real-world security challenges. Each educational theme consists of prelab activities, lab activities, and hands-on lab activities. By implementing authentic learning, we design and build portable lab for data poisoning vulnerability in LLM models on Google Colab. These hands-on labs can be accessed and practiced in real-time without the need for complex installations and configurations. This allows students to focus on learning concepts and increase their hands-on problem-solving skills.

Blockchain technology to build safe, decentralized systems for managing individual health records has become increasingly prevalent. As the number of personal health records (PHRs) increases, concerns about data privacy, security, and interoperability emerge, highlighting the need for standardized data integration with secured record linkage, privacy preservation, and quality control in research and analytical platforms. To address these challenges, we propose a novel Blockchain-based Patient Record Linkage System (BlockPRLS) for Big Data Analytics, leveraging confidentiality, integrity, and availability with a secured shared mechanism of PHRs. Moreover, the proposed solution significantly mitigates data gaps among operational health information systems (HIS) and clinical research infrastructure in low- and mid-income countries; where the international data standardization methods (e.g., LOINC, SONMED CT, OMOP Common Data Model) are not followed. Our extended framework presents a detailed architecture of a blockchain platform connecting with a mobile app- B2MAppH that connects patients, doctors, telehealth, and HIS, potentially able to transfer anonymous health records into the Central Data Repository (CDR) of a big data infrastructure. B2MappH is integrated with CDR, maintaining the privacy of the patient. It has been implemented in a private blockchain environment. Therefore, it provides an efficient solution for storing, linking, and sharing patient data, enabling better care coordination, big data research, and outcomes. Experimental evaluation shows the effectiveness of the system for both personal healthcare and big data analytics support.

Quantum machine learning (QML) is an emerging field of research that leverages quantum computing to improve the classical machine learning approach to solve complex real-world problems. QML has the potential to address cybersecurity-related challenges. Considering the novelty and complex architecture of QML, resources are not yet explicitly available that can pave cybersecurity learners to instill efficient knowledge of this emerging technology. In this research, we design and develop QML-based ten learning modules covering various cybersecurity topics by adopting student centering case-study based learning approach. We apply one subtopic of QML on a cybersecurity topic comprised of pre-lab, lab, and post-lab activities towards providing learners with hands-on QML experiences in solving real-world security problems. In order to engage and motivate students in a learning environment that encourages all students to learn, pre-lab offers a brief introduction to both the QML subtopic and cybersecurity problem. In this paper, we utilize quantum support vector machine (QSVM) for malware classification and protection where we use open source Pennylane QML framework on the drebin215 dataset. We demonstrate our QSVM model and achieve an accuracy of 95% in malware classification and protection. We will develop all the modules and introduce them to the cybersecurity community in the coming days.