Bao Gia Doan

Bao Gia Doan

Auto-generated profile, based on publicly available information

Bao Gia Doan

School of Computer Science, The University of Adelaide, Adelaide, SA, Australia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2021 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
YGYansong Gao
Yansong Gao
YKYeonjae Kim
Yeonjae Kim
BDBao Gia Doan
Bao Gia Doan
ZZZhi Zhang
Zhi Zhang
GZGongxuan Zhang
Gongxuan Zhang
Hyoungshick KimHyoungshick Kim
Hyoungshick Kim
Trojan attacks on deep neural networks (DNNs) exploit a backdoor embedded in a DNN model that can hijack any input with an attacker’s chosen signature trigger. Emerging defence mechanisms are mainly designed and validated on vision domain tasks (e.g., image classification) on 2D Convolutional Neural Network (CNN) model architectures; a defence mechanism that is general across vision, text, and audio domain tasks is demanded. This work designs and evaluates a run-time Trojan detection method exploiting STR ong I ntentional P erturbation of inputs that is a multi-domain input-agnostic Trojan detection defence across Vi sion, T ext and A udio domains—thus termed as STRIP-ViTA. Specifically, STRIP-ViTA is demonstratively independent of not only task domain but also model architectures. Most importantly, unlike other detection mechanisms, it requires neither machine learning expertise nor expensive computational resource, which are the reason behind DNN model outsourcing scenario—one main attack surface of Trojan attack. We have extensively evaluated the performance of STRIP-ViTA over: i) CIFAR10 and GTSRB datasets using 2D CNNs for vision tasks; ii) IMDB and consumer complaint datasets using both LSTM and 1D CNNs for text tasks; and iii) speech command dataset using both 1D CNNs and 2D CNNs for audio tasks. Experimental results based on more than 30 tested Trojaned models (including publicly Trojaned model) corroborate that STRIP-ViTA performs well across all nine architectures and five datasets. Overall, STRIP-ViTA can effectively detect trigger inputs with small false acceptance rate (FAR) with an acceptable preset false rejection rate (FRR). In particular, for vision tasks, we can always achieve a 0 percent FRR and FAR given strong attack success rate always preferred by the attacker. By setting FRR to be 3 percent, average FAR of 1.1 and 3.55 percent are achieved for text and audio tasks, respectively. Moreover, we have evaluated STRIP-ViTA against a number of advanced backdoor attacks and compare its effectiveness with other recent state-of-the-arts.

16 August 2022 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
BDBao Gia Doan
Bao Gia Doan
MXMinhui Xue
Minhui Xue
SMShiqing Ma
Shiqing Ma
EAEhsan Abbasnejad
Ehsan Abbasnejad
DRDamith Ranasinghe
Damith Ranasinghe
Deep neural networks (DNNs), regardless of their impressive performance, are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the decision of the model. We expose the existence of an intriguing class of spatially bounded, physically realizable, adversarial examples—Universal NaTuralistic adversarial paTches—we call TnTs, by exploring the super set of the spatially bounded adversarial example space and the natural input space within generative adversarial networks. Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective—achieving high attack success rates, and universal. A TnT is universal because any input image captured with a TnT in the scene will: i) misguide a network (untargeted attack); or ii) force the network to make a malicious decision (targeted attack). Interestingly, now, an adversarial patch attacker has the potential to exert a greater level of control—the ability to choose a location independent, natural-looking patch as a trigger in contrast to being constrained to noisy perturbations—an ability is thus far shown to be only possible with Trojan attack methods needing to interfere with the model building processes to embed a backdoor at the risk discovery; but, still realize a patch deployable in the physical world. Through extensive experiments on the large-scale visual classification task, ImageNet with evaluations across its entire validation set of 50,000 images, we demonstrate the realistic threat from TnTs and the robustness of the attack. We show a generalization of the attack to create patches achieving higher attack success rates than existing state-of-the-art methods. Our results show the generalizability of the attack to different visual classification tasks (CIFAR-10, GTSRB, PubFig) and multiple state-of-the-art deep neural networks such as WideResnet50, Inception-V3 and VGG-16. We demonstrate physical deployments in multiple videos at https://TnTattacks.github.io/.

2 August 2020 in arXiv
Verified
Preprint
Open access
PDF file
YGYansong Gao
Yansong Gao
BDBao Gia Doan
Bao Gia Doan
ZZZhi Zhang
Zhi Zhang
SMSiqi Ma
Siqi Ma
JZJiliang Zhang
Jiliang Zhang
Hyoungshick KimHyoungshick Kim
Hyoungshick Kim
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures, and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor.Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks. In some cases, an attacker can intelligently bypass existing defenses with an adaptive attack. Drawing the insights from the systematic review, we also present key areas for future research on the backdoor, such as empirical security evaluations from physical trigger attacks, and in particular, more efficient and practical countermeasures are solicited.

6 November 2026
Verified
Conference Paper
Open access
ABAarya Bodhankar
Aarya Bodhankar
AJAditya Joshi
Aditya Joshi
BDBao Gia Doan
Bao Gia Doan
TMThomas Marchant
Thomas Marchant
OLOscar Leslie
Oscar Leslie
FSFlora Salim
Flora Salim
Policymakers in defence and defence-aligned sectors must monitor rapidly evolving research alongside sector priorities relevant to operational and strategic needs. In practice, these sources are fragmented across heterogeneous formats, disjoint repositories, making capability discovery slow and difficult to audit. We present Didact, a prototype that integrates two sources: publicly available defence reports and policy documents from Australia, and a purpose-built knowledge graph derived from Australian research publications. Didact provides natural language conversations for policy-oriented workflows, and devises a composite retrieval-augmented generation (RAG) pipeline that allows synthesis of information from both sources. A key feature of Didact is an interactive Evidence Rail that presents retrieved document evidence and, when research-graph retrieval is used, visualises relevant entities and relationships. Automated evaluation on DoRA-QnA50 characterises Didact's retrieval quality, response quality, and runtime. While Didact has been co-developed as an academia-industry project for the Australian defence context, it is adaptable to other domains where knowledge is similarly fragmented and reliability is critical. A demonstration video is available here: https://youtu.be/KRtlq3LQ9WA.

5 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
SYShuiqiao Yang
Shuiqiao Yang
BDBao Gia Doan
Bao Gia Doan
PMPaul Montague
Paul Montague
OVOlivier De Vel
Olivier De Vel
TATamas Abraham
Tamas Abraham
SKSalil Kanhere
Salil Kanhere
Graph Neural Networks (GNNs) have achieved tremendous success in many graph mining tasks benefitting from the message passing strategy that fuses the local structure and node features for better graph representation learning. Despite the success of GNNs, and similar to other types of deep neural networks, GNNs are found to be vulnerable to unnoticeable perturbations on both graph structure and node features. Many adversarial attacks have been proposed to disclose the fragility of GNNs under different perturbation strategies to create adversarial examples. However, vulnerability of GNNs to successful backdoor attacks was only shown recently. In this paper, we disclose the TRAP attack, a Transferable GRAPh backdoor attack. The core attack principle is to poison the training dataset with perturbation-based triggers that can lead to an effective and transferable backdoor attack. The perturbation trigger for a graph is generated by performing the perturbation actions on the graph structure via a gradient based score matrix from a surrogate model. Compared with prior works, TRAP attack is different in several ways: i) it exploits a surrogate Graph Convolutional Network (GCN) model to generate perturbation triggers for a blackbox based backdoor attack; ii) it generates sample-specific perturbation triggers which do not have a fixed pattern; and iii) the attack transfers, for the first time in the context of GNNs, to different GNN models when trained with the forged poisoned training dataset. Through extensive evaluations on four real-world datasets, we demonstrate the effectiveness of the TRAP attack to build transferable backdoors in four different popular GNNs using four real-world datasets.

28 September 2020 in arXiv
Verified
Preprint
Open access
PDF file
BDBao Gia Doan
Bao Gia Doan
EAEhsan Abbasnejad
Ehsan Abbasnejad
DRDamith Ranasinghe
Damith Ranasinghe
We propose Februus; a new idea to neutralize highly potent and insidious Trojan attacks on Deep Neural Network (DNN) systems at run-time. In Trojan attacks, an adversary activates a backdoor crafted in a deep neural network model using a secret trigger, a Trojan, applied to any input to alter the model's decision to a target prediction---a target determined by and only known to the attacker. Februus sanitizes the incoming input by surgically removing the potential trigger artifacts and restoring the input for the classification task. Februus enables effective Trojan mitigation by sanitizing inputs with no loss of performance for sanitized inputs, Trojaned or benign. Our extensive evaluations on multiple infected models based on four popular datasets across three contrasting vision applications and trigger types demonstrate the high efficacy of Februus. We dramatically reduced attack success rates from 100% to near 0% for all cases (achieving 0% on multiple cases) and evaluated the generalizability of Februus to defend against complex adaptive attacks; notably, we realized the first defense against the advanced partial Trojan attack. To the best of our knowledge, Februus is the first backdoor defense method for operation at run-time capable of sanitizing Trojaned inputs without requiring anomaly detection methods, model retraining or costly labeled data.