publications

Selected publications in trustworthy AI, adversarial machine learning, and machine learning security.

2025

  1. AAAI
    bella.png
    Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks
    Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo, and 5 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2025
    arXiv HTML

2024

  1. ACSAC
    credibility.png
    On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World
    Bao Gia Doan, Dang Quang Nguyen, Callum Lindquist, and 7 more authors
    In Annual Computer Security Applications Conference, 2024
    arXiv
  2. ESORICS
    malware.png
    Bayesian Learned Models Can Detect Adversarial Malware for Free
    Bao Gia Doan, Dang Quang Nguyen, Paul Montague, and 6 more authors
    In European Symposium on Research in Computer Security, 2024
    DOI HTML

2023

  1. AAAI ’23
    feature-space.png
    Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness
    Bao Gia Doan, Shuiqiao Yang, Paul Montague, and 6 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2023
    HTML

2022

  1. TIFS
    tnt.png
    TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems
    Bao Gia Doan, Minhui Xue, Shiqing Ma, and 2 more authors
    IEEE Transactions on Information Forensics and Security, 2022
    HTML
  2. ICML
    information-gain.png
    Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
    Bao Gia Doan, Ehsan M. Abbasnejad, Javen Qinfeng Shi, and 1 more author
    In Proceedings of the 39th International Conference on Machine Learning, 2022
    HTML
  3. RAID
    Transferable Graph Backdoor Attack
    Shuiqiao Yang, Bao Gia Doan, Paul Montague, and 6 more authors
    In International Symposium on Research in Attacks, Intrusions and Defenses, 2022
  4. PhD
    Towards Robust Deep Neural Networks
    Bao Gia Doan
    University of Adelaide, 2022

2021

  1. TDSC
    Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks
    Yansong Gao, Yeonjae Kim, Bao Gia Doan, and 5 more authors
    IEEE Transactions on Dependable and Secure Computing, 2021

2020

  1. ACSAC
    februus.png
    Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
    Bao Gia Doan, Ehsan Abbasnejad, and Damith C. Ranasinghe
    In Annual Computer Security Applications Conference, 2020
    DOI HTML
  2. Survey
    Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
    Yansong Gao, Bao Gia Doan, Zhi Zhang, and 5 more authors
    arXiv preprint arXiv:2007.10760, 2020
    arXiv

For a complete and current list, visit my Google Scholar profile.