I am a Postdoctoral Research Fellow at UNSW Sydney, specialising in developing reliable Retrieval-Augmented Generation (RAG) systems that integrate large language models (LLMs) with external knowledge bases. 

My research focuses on optimising transformer architectures for improved semantic retrieval, implementing advanced prompt engineering techniques to reduce hallucination, and developing robust evaluation frameworks for RAG performance. 

I work extensively with vector embeddings, neural information retrieval, and fine-tuning methodologies to enhance the factual accuracy and reliability of LLM outputs in knowledge-intensive applications, while addressing scalability challenges in real-world RAG deployments across diverse domains.

Before joining UNSW, I completed my PhD and worked as a Postdoctoral Research Fellow at the University of Adelaide (Australia), focusing on the Robustness of deep neural networks.

Before my academic life, I spent nearly four years at Intel (Vietnam), working as a Senior Process and Equipment Engineer. 

For a more detailed overview of my professional experience, please take a look at my CV.

• July 2025 - I will serve as a Program Committee member for AAAI (CORE Rank: A*) and its special track AI Alignment (AIA) conference. 

• Feb 2025 - I will serve as a Program Committee for NeurIPS (CORE Rank: A*) conference.

• Jan 2025 - I will serve as a Program Committee for ICML (CORE Rank: A*) conference.

• Dec 2024 - AAAI'25 - Our paper titled Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks is accepted to the AAAI (CORE Rank: A*) conference in 2025. 

• Dec 2024 - ACSAC'2024 - Hawaii (USA) - I attended and presented our paper titled On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World

• Sep 2024 - ESORICS'2024 - Bydgoszcz (Poland) - I attended and presented our paper titled Bayesian Learned Models Can Detect Adversarial Malware For Free.

• 2024 - I served as a Program Committee for NeurIPS-2024, ICML-2024, ICLR-2024, ECCV-2024  and AAAI-2024 conferences.

• 2023 - I served as a Program Committee for NeurIPS-2023, ICCV-2023, AAAI-2023 conferences.

• 2022 - I served as a Program Committee for ICML-2022, ECCV-2022, CVPR-2022 conferences.

• Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks
  BG Doan, A Shamsi, XY Guo, A Mohammadi, H Alinejad-Rokny, ...
  AAAI Conference on Artificial Intelligence (AAAI-25, Rank A*), 2025.

• Bayesian Learned Models Can Detect Adversarial Malware For Free
  BG Doan, DQ Nguyen, P Montague, T Abraham, O De Vel, S Camtepe, ...
  European Symposium on Research in Computer Security (ESORICS, Rank A), 2024.

• On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World
  BG Doan, DQ Nguyen, C Lindquist, P Montague, T Abraham, O De Vel, ...
  Annual Computer Security Applications Conference (ACSAC, Rank A), 2024.

• Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness
  BG Doan, S Yang, P Montague, O De Vel, T Abraham, S Camtepe, ...
  AAAI Conference on Artificial Intelligence (AAAI-23, Rank A*), 2023.

• TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems
  BG Doan, M Xue, S Ma, E Abbasnejad, DC Ranasinghe
  IEEE Transactions on Information Forensics and Security (TIFS, Q1), 2022.

• Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
  BG Doan, EM Abbasnejad, JQ Shi, DC Ranasinghe
  International Conference on Machine Learning (ICML, Rank A*), 5309-5323, 2022.

• Februus: Input purification defense against trojan attacks on deep neural network systems
  BG Doan, E Abbasnejad, DC Ranasinghe
  Annual Computer Security Applications Conference (ACSAC - Rank: A) 2020, 897-912, 2020.

• Transferable Graph Backdoor Attack
  S Yang, BG Doan, P Montague, O De Vel, T Abraham, S Camtepe, ...
  Int. Symp. on Research in Attacks, Intrusions and Defenses (RAID, Rank A), 2022.

• Backdoor attacks and countermeasures on deep learning: A comprehensive review
  Y Gao, BG Doan, Z Zhang, S Ma, J Zhang, A Fu, S Nepal, H Kim
  arXiv preprint arXiv:2007.10760

• Design and evaluation of a multi-domain Trojan detection method on deep neural networks
  Y Gao, Y Kim, BG Doan, Z Zhang, G Zhang, S Nepal, DC Ranasinghe, ...
  IEEE Transactions on Dependable and Secure Computing (TDSC, Q1), 2021.

• Towards Robust Deep Neural Networks
  GB Doan
  University of Adelaide, 2022.