Dr. Bao Gia Doan

I am a machine learning researcher and Postdoctoral Research Fellow. My research specialises in the robustness and trustworthiness of deep neural networks, from convolutional neural networks to large language models and transformer architectures.

My work in adversarial machine learning develops attack and defence mechanisms for threats including adversarial examples, data poisoning, model inversion, and backdoor attacks. It spans both machine learning for security and security for machine learning.

I also investigate privacy-preserving techniques such as differential privacy and federated learning. More recently, I have been building secure retrieval-augmented generation systems with open-source LLMs, addressing prompt injection, retrieval poisoning, hallucination mitigation, and trustworthy AI deployment.

Current position

At UNSW Sydney, I develop reliable retrieval-augmented generation systems that connect large language models with external knowledge bases. My work covers semantic retrieval, prompt engineering, vector embeddings, neural information retrieval, fine-tuning, evaluation, and the scalability of knowledge-intensive applications.

Previous positions

Before joining UNSW, I completed my PhD and worked as a Postdoctoral Research Fellow at the University of Adelaide, focusing on the robustness of deep neural networks. Before academia, I spent nearly four years at Intel Vietnam as a Senior Process and Equipment Engineer.

For a detailed overview, see my CV.