Explore a range of computer science research internships to complete as part of your degree during the semester break.
The following internships listed are due to take place across the Summer break.
Applications open 10th September and close 30th September 2025.
Supervisors: Dr Zhanna Sarsenbayeva, Dr Anusha Withana
Eligibility: To do well in this project you will need strong programming, independent learning, and independent decision-making skills.
Project Description:
As technology becomes increasingly embedded in our daily lives, artificial agents, ranging from social robots to virtual assistants, are being designed to interact with humans in more lifelike and relatable ways. One key approach is anthropomorphism:embedding agents with human-like qualities such as expressive faces, natural-sounding voices, or relatable language. While these features are believed to foster emotional connection, the specific impact of different anthropomorphic embodiments on users’ empathy is still not fully understood. Systematic investigation in this area can inform the design of future AI systems that support meaningful, empathetic human-agent interactions.
This project explores how different forms of anthropomorphism (e.g.: physical/facial expressions, voice, and text-based interactions) influence empathic responses in humans.
By conducting controlled experiments, the research will shed light on which embodiment(s) most effectively elicit empathy, with applications in human-robot interaction, virtual agents, and digital communication.
Scope:
Expected outcome:
Requirement to be on campus: Yes, *dependent on government’s health advice.
Supervisors: A/Prof. Anusha Withana, Dr Zhanna Sarsenbayeva, Yihao Dong
Eligibility:
Project Description:
People with vision impairment (PVI), including those with low vision or blindness, face challenges in understanding their surroundings. Traditionally, they rely on white canes or guide dogs for navigation. However, limited research has explored how tactile cues, such as vibrotactile or electrotactile feedback, can help PVI perceive their environment from a distance. For example, providing hierarchical spatial information through tactile feedback remains underexplored.
This project is in its early stages and aims to explore the feasibility of using tactile cues to convey environmental information. We will start with simple geometric cues and gradually investigate more complex spatial details. By identifying effective tactile feedback strategies, this research seeks to lay the groundwork for future innovations in assistive technology for PVI.
Requirement to be on campus: Yes, *dependent on government’s health advice.
Supervisor: Dr Sri Aravindakrishnan Thyagarajan
Eligibility Criteria: WAM>85
Project Description:
Transactions in blockchains rely on game theoretic incentives for users to behave honestly. However, these incentives are designed with assumptions that are shown to be too strong in current systems. We have many instances of practical attacks that exploit these assumptions. The goal of this project is to study game theoretic mechanism designs that achieve stronger fairness notions for highly impactful applications in decentralised settings like blockchains.
At the end of the project, the student will have a better understanding of how protocols are designed for blockchain systems and tools to analyse them formally.
The project will be theoretical in nature.
Requirement to be on campus: No
Supervisor: Dr Sri Aravindakrishnan Thyagarajan
Eligibility: WAM>85
Project Description:
As blockchain systems transition from classical cryptography to post-quantum security, the core challenge lies in replacing existing cryptographic components with algorithms resilient against quantum attacks. Following the recent NIST standardisation, we now have promising post-quantum candidates for digital signatures and encryption, expected to see widespread adoption within the next decade.
This project will explore how these emerging post-quantum cryptographic primitives can be integrated into blockchain protocols, with a particular emphasis on achieving fairness in distributed applications. Since these algorithms are still in the early stages of deployment, there is significant scope to study their performance, scalability, and suitability for real-world blockchain environments.
By the end of the project, the student will gain expertise in post-quantum cryptography, understand the security implications of quantum threats for blockchain systems, and learn how to design applications that are both quantum-resilient and fair by design.
Requirement to be on campus: No
Supervisor: Dr Sri Aravindakrishnan Thyagarajan
Eligibility: WAM>85
Project Description:
As quantum computing advances, we are left wanting to develop secure and fair solutions when information passed around is no longer classical, but quantum states. In this project we will study about certain basic quantum computing principles and how we can adapt cryptographic techniques to capture these principles to design secure solutions.
The project will be theoretical in nature where we will explore ideas related to certified proof of deletion, one-time programs and other similar new ideas in quantum cryptography and develop new ones.
At the end of the project the student will be trained in understanding quantum post quantum security and how modern applications can be made fundamentally more secure and fair.
Requirement to be on campus: No
Supervisor: Dr Qiang Tang
Eligibility: WAM > 80, excited about building an E2EE secure Internet
Project Description:
There are massive data breach incidents and cyber attacks on digital supply chain frequently, however, essentially all Internet services nowadays except secure messaging tools such as Signal, WhatsApp offer end to end security.
In this project we will investigate end to end secure online collaboration tools such as Cloud Storage, GoogleDoc, GoogleSheets.
Important references:
https://eprint.iacr.org/2025/1208
https://www.usenix.org/conference/usenixsecurity22/presentation/chen-long
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: Dr Qiang Tang
Eligibility: WAM > 80, excited about building an E2EE secure Internet
Project Description:
There are massive data breach incidents and cyber attacks on digital supply chain frequently, however, essentially all Internet services nowadays except secure messaging tools such as Signal, WhatsApp offer end to end security.
In this project we will investigate end to end secure online collaboration, particularly on the web version of github that enables easy code review etc.
Important references:
https://eprint.iacr.org/2025/1208
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor:Prof. Joseph Davis
Eligibility: WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application
Project Description:
The complexity levels associated with AI systems is undergoing a massive increase as developers shift their focus to building Large Language Model (LLM) agents that can act in a goal-directed manner by planning and making decisions autonomously and using tools while interacting with the external environments. While the risks associated with the first generation of AI systems are relatively well understood, agentic structures not only amplify the known risks but also introduce qualitatively new types of risks.
This project will involving a deep dive into the range of risks and associated with agentic AI and their implications at both organisational and societal levels. This will be followed by an investigation into the technical approaches to mitigating the identified risks.
Given that Knowledge Graphs (KGs) provide a structured knowledge representation layer that enables most industry-strength agentic systems to scale, the project will also require the development of Agent GRC ontology and knowledge graph that will be part of the technical stack for implementing agent risk assessment and compliance models.
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: Dr Sasha Rubin
Eligibility: WAM >= 85, and HD in at least one math-heavy UoS)
Project Description:
Planning is part of the symbolic/logic approach to AI which involves finding a finite- state program that tells an agent what to do in every state. The states and possible actions are described declaratively. See, e.g., https://research.ibm.com/projects/ai-planning
One approach to building a planner is to reduce the given planning problem to the satisfiability problem, and implement this as a reduction to SAT solvers or in declarative programming languages such as ASP (https://potassco.org/).
There are a few possible topics for this project, depending on the interest and skill of the student e.g., Build a declarative planner for modern (decision-theoretic) solutions such as non-dominated solutions. e.g., Build a declarative planner that solves “lifted planning” for standard solutions (such as strong or strong-cyclic) by reducing to automated theorem proving.
All of the work will have some mathematical component, and may include a coding component depending on the topic. This project will suit a student who achieved an HD in a course on Theoretical Computer Science.
Requirement to be on campus: No
Supervisor: Dr Sasha Rubin
Eligibility: WAM >= 85, and HD in at least one math-heavy UoS
Project Description:
Decision problems in logic typically focus on determining whether sentences of first-order logic (FO) selected from a given class are logically valid or not. Famous such classes known to have decidable problems are the Gödel class (sentences that start with two existential quantifiers followed by any number of universal quantifiers) and the two-variable fragment of FO (sentences that use at most two-individual variables).
Gurevich and Shelah provided a novel proof of the finite model property (that every satisfiable formula has a finite model) and decidability for the Gödel class using the probabilistic methods, particularly using finite random structures.
The goal of this project is to understand the reach and possible limitations of probabilistic methods in establishing the finite model property and decidability for the two-variable fragment of first-order logic.
This project will suit a student who is very familiar with first-order logic, and has a background in Pure Mathematics or Theoretical Computer Science.
Requirement to be on campus: No
Supervisor: Dr Suranga Seneviratne
Eligibility:
Project Description:
Behavioural biometrics are crucial for continuous authentication, particularly as zero-trust architectures gain prominence. Systems can verify user identity in real-time by analysing multimodal data streams – such as keystroke dynamics, mouse movements, gait, and touch patterns. This continuous verification enhances security by detecting anomalies and preventing unauthorised access. However, real-world data is often noisy, incomplete, and subject to environmental variability, posing significant challenges for reliable classification and detection.
To this end, this project offers two potential directions. The first focuses on developing and evaluating JEPA-based models by Meta to learn robust representations from behavioural biometrics data, addressing inconsistencies and improving predictive accuracy.
The second is to explore whether the in-context learning abilities of sensor foundation models can be used for reliable continuous user authentication. This direction is based on the recent work from Google.
Requirement to be on campus: No
Supervisor: Prof. Jinman Kim
Eligibility:
Majors in:
Preferred Skills:
Desired Traits:
Project Description:
This project aims to design and develop a deep learning (DL) algorithm to remotely monitor patients doing physiotherapy exercises. It will involve recognising the type of exercise performed, correct movements, successful repetition, and progression over time. These patients are preparing for major surgeries and exercises are essential requirement for their wellbeing at the Nepean Hospital.
The project student will develop a state-of-the-art DL model for analysis of home-based exercises using video feed from patient’s devices (smartphones/tablets). The model will extract key metadata (3-D coordinates of key body parts) directly from video feeds during execution, eliminating the need to upload full videos to preserve patient privacy. The project will leverage advanced open source repository of algorithms and data sets to build the model.
Key tasks include:
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: Prof. Jinman Kim
Eligibility:
Majors in:
Preferred Skills:
Desired Traits:
Project Description:
This project will develop a proof-of-concept software system for interactive segmentation of complex medical image datasets. Complexity is defined as the imaging being multi-modal (PET/CT), rare unsees diseases, noisy and poorly defined structures, and sequential images data (multiple time points).
We will exploit the rapid advances in prompt-based segmentation algorithms that are built on foundation models such as SAM and explore different prompting strategies (clicks, scribbles, texts, relevant samples etc), and design an optimised solution for our complex cases.
The project will make use of wide array of open source prompt segmentation methods (e.g., SAM / biomedCLIP) and evaluate them using public datasets (e.g., autoPET).
The project will work closely with a research team that has expertise in multi-modal medical image segmentation, and potentially in partnership with hospital partners.
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: Dr Rahul Gopinath
Eligibility: You will work with the supervisor directly for this project. You should be a fast learner. Excellent skills in programming, using LLMs, as well as the ability to work independently are required.
Project Description:
For decades, software testing research has been built on the "competent programmer hypothesis" - the assumption that most bugs in code are relatively simple mistakes made by otherwise skilled programmers, like using the wrong comparison operator or being off-by-one in a loop condition. This assumption underlies mutation testing, a powerful technique that evaluates test suites by introducing small, artificial faults into programs to see if the tests can catch them. However, as Large Language Models (LLMs) like GPT-4 and Claude increasingly write code, we face a fundamental question: do these AI systems make the same kinds of mistakes that human programmers do?
This research investigates whether the error patterns of LLM-generated code follow the same distributions as human errors. By having LLMs describe functions in natural language and then re-implement them, we can study how their error models differ from humans and determine whether our existing testing methodologies remain effective in a world where much of our code may be written by artificial intelligence rather than human hands.
This project may be extended to an Honours thesis with the supervisor, and if completed successfully could be the basis of a publication at a top SE venue.
(In your application, please indicate if you are interested in a Honours application with the supervisor).
Requirement to be on campus: No
Supervisors: Prof. Seokhee Hong and Dr Amyra Meidiana
Eligibility: Data Structure and Algorithms, Programming (Java, C++, Python, Javascript)
Project Description:
Technological advances have increased data volumes in the last few years, and now we are experiencing a “data deluge” in which data is produced much faster than it can be understood by humans.
These big complex data sets have grown in importance due to factors such as international terrorism, the success of genomics, increasingly complex software systems, and widespread fraud on stock markets.
Visualisation is a powerful tool to compute good geometric representation of abstract data to support analysts to find insights and patterns in big complex data sets.
This project aims to design, implement and evaluate new visualisation algorithms for scalable and faithful visualisation of big complex data, to enable humans to find ground truth structure in big complex data sets, such as social networks and biological networks.
These new visualisation methods are in high demand by industry for the next generation visual analytic tools.
Requirement to be on campus: Yes * dependent on government’s health advice.
Supervisor: A/Prof. Chang Xu
Eligibility:
Project Description:
We are developing an advanced system that can identify food items on a plate from images, estimate portion sizes, and calculate corresponding nutritional values such as calories, protein, fat, and carbohydrates. This technology integrates computer vision, deep learning, and nutritional databases to deliver accurate, real-time analysis. Potential applications include personal health tracking, dietary management, smart dining services, hospital meal monitoring, and elderly care nutrition management.
Requirement to be on campus: Yes * dependent on government’s health advice.
Supervisor: A/Prof. Chang Xu
Eligibility:
Project Description:
Recently, a large number of large-scale visual-language-action models (VLAs) have emerged. However, there are numerous issues within these models that urgently require reinforcement learning to address. One specific issue is that existing visual-language models often unfollow the text input and instead execute actions based solely on visual input. Reinforcement learning has been widely used in recent years to solve specific problems in neural networks. This project aims to enhance the ability of VLAs to follow the text input through reinforcement learning methods.
Requirement to be on campus: Yes * dependent on government’s health advice..
Supervisor: A/Prof. Nguyen Tran
Eligibility: Machine learning Python coding
Project Description:
Large language models (LLMs) have revolutionized various real-world applications. However, their high-end hardware requirements often limit accessibility for many researchers. Our project aims to democratize the use of such transformative technology through distributed computing. By leveraging multiple GPUs at edge networks, we enable efficient inference and fine-tuning of LLMs, making cutting-edge AI research feasible and more inclusive. This approach not only enhances computational efficiency but also broadens the scope of research possibilities by reducing the barrier to entry for utilizing state-of-the-art LLMs.
Requirement to be on campus:Yes * dependent on government’s health advice.
Supervisors: Dr Katy Gero, Dr Kanchana Thilakarathna, Dr Clément Canonne
Eligibility: Experience with ML or LLM pipelines or large-scale data collection
Project Description:
As generative AI, especially large language models (LLMs), continue to be adopted in various sectors, the importance of adapting these models to a particular cultural context increases. This project will investigate how develop an “Australia-first” language model. Such a model would be aligned with Australian values and produce culturally-relevant responses. Projects include: analyzing the technology stacks that other countries have or are proposing in sovereign AI projects, designing custom LLM benchmarks for Australian values and knowledge, interviewing key stakeholders about how to determine Australian priorities or values for a national LLM, measuring and comparing cultural differences between existing LLMs, developing an RLHF pipeline to embed Australian values in a model, sourcing and documenting key datasources for fine-tuning an Australian LLM, assessing the costs associated with various proposals.
This project aims to take concrete steps towards building an Australian language model.
Requirement to be on campus: Yes * dependent on government’s health advice.
Supervisors: Dr Katy Gero, Dr Kazjon Grace, Prof.. Jen Scott Curwood
Eligibility: Experience with ML or language model pipelines, experience or interest in creative writing.
Project Description:
As language models have grown in popularity, in size, in capabilities --- they have also become more boring. Among artists and writers, there is nostalgia for the GPT-2 era models which were less capable but were also weirder, quirkier, and more artistically interesting. Additionally, artists often have ethical concerns with using large commercials models, such as concerns about the legality of the training data, the environmental costs, and the goals of the parent organizations.
This project would have an eager student: 1) select or develop “creative” benchmarks to evaluate language models, 2) fine-tune a small language model on an ethically sourced creative writing dataset, and 3) evaluate the model according to the selected benchmarks.
Requirement to be on campus: Yes * dependent on government’s health advice.
Supervisor: Dr Mohammad Polash
Eligibility:
Project Description:
With the rapid rise of generative AI, students increasingly rely on AI-generated code to solve programming tasks. While this accelerates problem-solving, it often undermines their confidence in writing code independently. This project addresses this challenge by developing an educational tool that leverages GenAI to strengthen students’ programming skills and computational thinking.
The tool generates intentionally buggy code based on a given problem specification and prompts students to critically analyze it. Learners will be tasked with identifying logical, syntactical, or structural errors, encouraging a deeper understanding of programming concepts. Additionally, the tool guides students to translate problem requirements into step-by-step computational logic, reinforcing their ability to design solutions before coding.
By shifting the focus from passive code consumption to active problem-solving and debugging, the project aims to build students’ confidence, autonomy, and resilience in programming, equipping them with skills crucial for both academic and professional success.
Requirement to be on campus: No
Supervisors: Dr Muhammad Sajjad Akbar and Dr Mohammad Polash
Eligibility: WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application
Project Description:
This project seeks to design and evaluate an AI-powered accessibility tool that will support Engineering students with special needs, including those with visual impairments and other learning challenges.
The research will investigate how adaptive AI technologies such as speech-based interfaces, multimodal content conversion, and personalized learning assistance can be integrated into higher education. Based on the findings, the project will culminate in the development of a practical tool that enables students with special needs to access, engage with, and contribute to engineering coursework more effectively.
The project will contribute to a stronger research culture by combining expertise in engineering, AI, and inclusive education. It will also open new avenues for PhD recruitment by establishing a focused research stream on accessibility and human-AI interaction. Supervisors will benefit from novel research outcomes, new collaborative opportunities, and a tangible tool that demonstrates real-world impact.
Requirement to be on campus: No
Supervisors: Prof. Zhiyong Wang (CS), ZuFu Lu (BME), Prof. Hala Zreiqat (BME)
Eligibility:
Project Description:
Recent advances in artificial intelligence (AI) have significantly enhanced our ability to analyze complex biological systems, including the identification of cell types, states, and dynamic transitions. Emerging studies demonstrate the potential of AI to observe and predict cell fate transitions by analyzing imaging and transcriptomic datasets. Building on this foundation, we propose the development of a novel AI-based tool that leverages integrated transcriptomic data from existing literature to predict the bone regeneration potential of biomaterial scaffolds.
This tool aims to provide an economical and scalable solution for screening scaffold materials by accurately forecasting their regenerative outcomes. To ensure robustness and real-world applicability, the model will undergo thorough validation using both in vitro and in vivo approaches. Ultimately, this project seeks to deliver a reliable, cost-effective AI platform to accelerate the development of biomaterials for bone tissue engineering.
Requirement to be on campus: No
Supervisor: Prof. Zhiyong Wang
Eligibility:
Project Description:
Recent breakthroughs in Artificial Intelligence (AI) have led phenomenal success in protein structure prediction, which presents immense opportunities to accelerate the innovations in structure based drug discovery. This project aims to develop novel generative AI methods by exploiting the structures of proteins for effective drug design.
Supervisor: A/Prof. Wei Bao
Eligibility: The student should have prior experience in machine learning and distributed computing. The project is well-suited for students who are motivated to take Research Pathway Project, Honours Research Project, MPhil, or PhD.
Project Description:
Federated learning (FL) enables collaborative model training without centralising data, but it raises critical concerns about the “right to be forgotten.” Federated unlearning (FU) aims to remove the impact of specific data from trained models. However, existing methods often overlook adversarial environments, where malicious data removal requests could compromise the model’s integrity and reliability. This project will explore novel methods to make FU algorithms more robust and efficient against adversarial behaviours, while ensuring model accuracy and fairness.
The student will design algorithms that can identify and mitigate the risks of malicious removal requests. The work will involve implementing these algorithms, and conducting experiments on benchmark datasets.
Requirement to be on campus: Yes *dependent on government’s health advice
Supervisor: A/Prof. Xiuying Wang
Eligibility:
Project Description:
This project aims to accelerate whole-body PET/MR acquisition by applying image-domain super-resolution to reconstructions from undersampled k-space data. While super-resolution techniques have been widely studied in localized MRI applications such as the brain, knee, or heart, there is currently few research addressing whole-body MRI reconstruction. Whole-body imaging is considerably more challenging due to its large field-of-view, heterogeneous anatomy, and variable contrast, yet it is of growing clinical importance in oncology and systemic disease evaluation.
By focusing on super-resolution for whole-body MR, this project tackles a critical gap in the field and explores how deep learning can enable high-quality reconstruction from undersampled acquisitions. The expected outcome is a significant reduction in scan time without compromising diagnostic value, providing both technical advances in medical image reconstruction and practical benefits for the broader adoption of PET/MR in clinical workflows.
Requirement to be on campus: Yes *dependent on government’s health advice
Supervisors: Prof. Alan Fekete, A/Prof. Uwe Roehm, Dr Danushka Liyanage
Eligibility: Some experience with measuring dbms performance; also experience with PostgreSQL or Neo4J is desirable
Project Description:
The supervisors recently published an extension of the YCSB benchmark system to cover situations where some database records get longer over time. This project will use this framework to measure performance of extra dbms platforms such as PostgreSQL, Neo4J, etc, and then the project will analyse the results offering insights into scalability, efficiency, and trade-offs across platforms. The project may also add more workloads or metrics to the benchmark.
Requirement to be on campus: No
Supervisors: Dr Jonathan Kummerfeld, Prof. Alan Fekete (with Dr Anna Liu from Axon25)
Eligibility: Some knowledge of machine learning particularly of LLMs; knowledge of health care processes is desirable.
Project Description:
This project will see how to use domain-specific datasets to improve the effectiveness of general language models for the special case of dealing with conversations in the aged-care setting.
Requirement to be on campus: No
Supervisors: Dr Rahul Gopinath, Prof. Alan Fekete, A/Prof. Uwe Roehm, Dr Danushka Liyanage (with Prof. Scholz from Fantom Foundation)
Eligibility: Some experience with automated testing; also experience with Go language is desirable
Project Description:
This project extends recent work by the supervisors and a vacation student, applying fuzzing to test the database layer beneath the Ethereum blockchain. The aim is to automatically generate diverse test cases that probe how database operations are handled, exposing potential inconsistencies or failures. The project will also include techniques for log reduction, trimming execution traces to isolate the root causes of observed issues. Through this process, it will assess the robustness of the Ethereum database layer, while contributing improved methods for automated fault detection and diagnosis in blockchain systems.
Requirement to be on campus: No
Supervisors: Prof. Alan Fekete (with Dr Anna Liu from Axon25)
Eligibility: Experience with using cloud platforms such as AWS (at least some of AWS Lambda, Cognito, DynamoDB, Bedrock), and building data-backed applications. Understanding of the health care system is desirable.
Project Description:
This project will extend the capabilities developed in a previous vacation project which used Generative AI tools such as AWS Bedrock to create a virtual assistant which can enhance the productivity of health care providers, such as nurses in a hospital, or carers in an age care home.
Requirement to be on campus: No
Supervisors: A/Prof. Anusha Withana, Dr Tegan Cheng
Eligibility: Experience in 3D printing and 3D design, Blender, and physics simulation tools like ANSYS or COMSOL, programming skills in Python or C++ will be given precedence.
Project Description:
Children with cerebral palsy often face challenges in walking due to muscle tightness, poor balance, or coordination issues, and ankle-foot orthoses (AFOs) are commonly used to support and improve their walking ability. These devices can play a crucial role in enhancing mobility and independence. However, many AFOs are based on standard designs and do not fully account for each child's unique movement patterns, comfort, or specific therapeutic needs. This mismatch can reduce the effectiveness of the AFO and even cause discomfort or poor posture over time.
In this project, we focus on analysing the gait patterns of children with cerebral palsy before and after wearing redesigned AFOs to better understand how different designs influence movement. Using this data, we aim to develop an automated system that recommends personalised, optimised AFO designs tailored to each child's specific needs, making the process more efficient for clinicians and ultimately improving outcomes for children with cerebral palsy.
Requirement to be on campus: Yes *dependent on government’s health advice
Supervisors: A/Prof. Anusha Withana
Eligibility: You will work with the supervisor and a PhD student, and we expect you are a fast learner. Familiarity with point cloud processing required. Blender proficiency highly desirable.
Project Description:
This project explores the use of point cloud processing to enable customisation of 3D objects by seamlessly integrating and modifying them. By leveraging point cloud data from 3D/LiDAR scans, the system allows users to upload their own 3D models and easily mix and match with existing virtual assets. The project focuses on aligning and registering point clouds to customise objects’ shapes, sizes, and textures in real time. This tool has potential impacts for industries like product design, fashion, architecture, and gaming, where users can personalise designs and create bespoke objects or environments.
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: Dr Katy Gero
Eligibility: Experience with qualitative methods (e.g. interviewing) and basic web development skills.
Project Description:
Due to the rapid introduction and adoption of large language models (LLMs) in universities, there is a lack of understanding of their impact on writing education. Much work has reported positive effects of generative AI on writing. However, there is also evidence that the use of generative AI may accumulate 'cognitive debt' and decrease or change the nature of critical thinking. This project investigates how teachers and students can use generative AI to improve learning outcomes in writing while safeguarding students' critical thinking.
The research will involve: 1) exploring current usage of generative AI in university writing education; 2) prototyping and evaluating novel, learning-focused interventions.
Requirement to be on campus: Yes *dependent on government’s health advice.
Supervisor: A/Prof. Lijun Chang
Eligibility: Good algorithm design and C (or C++) programming skills
Project Description:
We are nowadays facing a tremendous amount of large-scale social networks with millions or billions of edges. Thus, there is a need of designing efficient algorithms for processing large-scale graphs. In this project, our aim is to design efficient algorithms to speed up graph processing on ever-growing large graph datasets. The problem that we will be investigating is efficiently finding a large near-clique over a large sparse graph.
Requirement to be on campus: No
Supervisor: Dr Hazem El-Alfy
Eligibility: Student took a Machine Learning or AI class and has excellent Python coding skills using the Keras or PyTorch library.
Project Description:
Medical imaging datasets are often limited due to privacy concerns and high annotation costs. This hinders the development of robust AI models. Traditionally, data augmentation techniques such as cropping, rotation, and flipping have been used to address this issue. This project aims to explore more robust generative models, such as GANs or diffusion models, to create realistic synthetic medical images for data augmentation. The student will review recent literature on generative AI in medical imaging, select an open-source dataset (e.g., chest X-rays or skin lesion images), and implement a pipeline to generate synthetic samples.
The impact of synthetic data on model performance will be evaluated by training a baseline classifier with and without augmentation. This research addresses the challenge of data scarcity in healthcare AI and could lead to improved diagnostic accuracy. If results are promising, the work may be submitted to a computer vision or medical imaging conference.
Requirement to be on campus: No
Supervisor: Dr Hazem El-Alfy
Eligibility: Student took a Machine Learning or AI class and has excellent Python coding skills using the Keras or PyTorch library.
Project Description:
Predicting student performance is essential for early intervention and personalised learning strategies. This project explores deep learning techniques for modelling academic performance as a time-series problem. Using sequential quiz scores, the student will investigate architectures such as LSTM, GRU, and Transformer models to predict final exam outcomes or overall performance. The work involves reviewing recent literature on educational data mining, implementing sequence models, and evaluating their accuracy against traditional regression approaches.
A proprietary dataset of 1,000 students with 10 quiz scores each will be used, and results will be benchmarked against a public dataset (e.g., UCI Student Performance or Kaggle’s Student Exam Scores). This research aims to demonstrate the potential of sequence modelling in educational analytics and could lead to improved prediction systems for academic success. Promising results may be submitted to conferences in AI and education.
Requirement to be on campus: No
Supervisor: Dr Hazem El-Alfy
Eligibility: Student took a Machine Learning or AI class and has excellent Python coding skills using the Keras or PyTorch library.
Project Description:
Potholes are a common scene in NSW streets after wet weather. It is estimated that the cost of repairing them reached up to $4 billion dollars in 2022 [1]. Compensations paid to the owners of damaged cars and handling liability claims also add up to the bill.
This project aims to devise an artificial intelligence software tool to detect potholes in images. Images can be collected by UAVs or traffic cameras, but that is out of the scope. So far, councils have relied on residents to report potholes in their areas, but this is a slow process which results in more cars getting damaged by the time action is taken.
The student participating in this project will survey the recent literature in the area, choose appropriate large image datasets and develop a deep-learning architecture to detect potholes. If promising, we can publish the results of this research in a reputable computer vision conference or journal.
[1] https://www.smh.com.au/national/nsw/pothole-repair-bill-soars-to-4b-record-20230717-p5dowx.html
Requirement to be on campus: No
Supervisor: Prof. Athman Bouguettaya
Eligibility: WAM>85
Project Description:
The proliferation of AI-generated images presents a significant challenge in verifying their authenticity. Traditional image verification methods often fall short against the advanced techniques employed by generative AI, making it difficult to distinguish between genuine and AI-created images. We propose an innovative approach to address this issue by focusing on the subtle traces that generative AI algorithms leave in the metadata of images. By detecting and analysing these indicators, we aim to assess the trustworthiness of AI-generated images with greater accuracy.
Our method will involve developing specialized tools to identify these metadata patterns, enabling us to differentiate between authentic and AI-generated images more effectively. This approach not only enhances the detection of untrustworthy content but also contributes to maintaining the integrity of online visual media. Through this research, we seek to provide a reliable solution for the growing challenge of AI-generated image verification in an increasingly digital world.
Requirement to be on campus: Yes *dependent on government’s health advice..
Supervisor: Prof. Athman Bouguettaya
Eligibility: WAM>85
Project Description:
As social media continues to evolve, the challenge of identifying fake audio becomes increasingly complex. Traditional approaches that rely on acoustic features or basic metadata analysis often fail to capture the nuanced semantics that distinguish authentic speech from manipulated or generated content. We propose offering fake audio detection as a service, powered by advanced models such as RoBERTa, T5, and GPT, trained to understand the contextual and semantic patterns in speech. By leveraging these models to analyze deeper linguistic and acoustic cues, the service aims to deliver more accurate and reliable detection of untrustworthy audio shared on social media platforms.
Requirement to be on campus: Yes*dependent on government’s health advice
Supervisor: Prof. Athman Bouguettaya
Eligibility: Good programming background in Python, and good knowledge on Algorithms
Project Description:
The Internet of Things (IoT) is transforming our world into a seamlessly connected ecosystem of smart devices. These devices collaborate by sharing resources—such as energy, computation, or Wi-Fi—through IoT service crowdsourcing. However, such IoT services could be exploited; for example, a consumer might misuse a Wi-Fi hotspot to launch a Denial-of-Service (DoS) attack.
Trust Management frameworks have been introduced to address these risks by establishing and maintaining trust. While they provide robust trust assessment methods, a critical challenge remains: ensuring the integrity of trust information. Since distributed entities are responsible for storing and managing trust data, they may tamper with it, making the system vulnerable to internal attacks.
The rise of AI tools, such as ChatGPT, has further lowered the barrier for adversaries, enabling even low-skilled actors to manipulate trust data with alarming sophistication. To counter this emerging threat, this project aims to explore AI-based tampering detection to detect AI-assisted tampering in trust information.
Requirement to be on campus: Yes*dependent on government’s health advice
.Supervisor: Prof.. Athman Bouguettaya
Eligibility: Good Programming Skills; Data Handling and Management Skills; Experience in Drone Flight Simulators will be a plus
Project Description:
A continuous expansion of urban areas is leading to an increased demand for instant deliveries from warehouses to customers' doorsteps. Unmanned Aerial Vehicles (UAVs) or drones have the potential to serve customers with timely and cost-effective deliveries. Drones usually operate in a skyway network, which is an interconnected set of nodes. The nodes are building rooftops that serve as recharging stations or delivery destinations for drones. Drones may recharge at nodes for long distance deliveries as they are constrained by limited battery capacity. These nodes are connected through skyway segments, which multiple drones may share at the same time to transit between nodes. However, managing drone traffic in congested urban environments presents significant challenges.
The risk of aerodynamic interference among multiple drones operating in shared skyway segments may impact drone delivery efficiency and safety. The focus of this project is to develop an AI-driven stabilization system for drones to counteract the effects of interference caused by peer drones or environmental factors. We leverage machine learning techniques and real-time sensor data to identify aerodynamic disturbances and generate corrective control actions. The goal is to ensure safe and efficient operation of drones in a shared skyway network.
Requirement to be on campus: Yes*dependent on government’s health advice
Last updated 7th September 2025.
