Hai Dong

Dr. Hai Dong

RMIT University, Melbourne, Victoria, Australia
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 October 2014 in Journal of Network and Computer Applications
Verified
Journal Article
Closed access
LSLe Sun
Le Sun
HDHai Dong
Hai Dong
FHFarookh Khadeer Hussain
Farookh Khadeer Hussain
Omar Khadeer HussainOmar Khadeer Hussain
Omar Khadeer Hussain
ECElizabeth Chang
Elizabeth Chang

24 March 2017 in Communications of the ACM
Verified
Journal Article
Open access
PDF file
ABAthman Bouguettaya
Athman Bouguettaya
MSMunindar Singh
Munindar Singh
MHMichael Huhns
Michael Huhns
QSQuan Z. Sheng
Quan Z. Sheng
HDHai Dong
Hai Dong
MPMichael Papazoglou
Michael Papazoglou
Mapping out the challenges and strategies for the widespread adoption of service computing.

6 April 2023 in Information and Software Technology
Verified
Journal Article
Closed access
HCHanting Chu
Hanting Chu
PZPengcheng Zhang
Pengcheng Zhang
HDHai Dong
Hai Dong
YXYan Xiao
Yan Xiao
SJShunhui Ji
Shunhui Ji
WLWenrui Li
Wenrui Li

1 April 2016 in Future Generation Computer Systems
Verified
Journal Article
Closed access
LSLe Sun
Le Sun
JMJiangang Ma
Jiangang Ma
YZYanchun Zhang
Yanchun Zhang
HDHai Dong
Hai Dong
FHFarookh Khadeer Hussain
Farookh Khadeer Hussain

21 November 2014 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
ZYZhen Ye
Zhen Ye
Sajib MistrySajib Mistry
Sajib Mistry
ABAthman Bouguettaya
Athman Bouguettaya
HDHai Dong
Hai Dong
We propose a cloud service composition framework that selects the optimal composition based on an end user's long-term Quality of Service (QoS) requirements. In a typical cloud environment, existing solutions are not suitable when service providers fail to provide the long-term QoS provision advertisements. The proposed framework uses a new multivariate QoS analysis to predict the long-term QoS provisions from service providers' historical QoS data and short-term advertisements represented using Time Series. The quality of the QoS prediction is improved by incorporating QoS attributes' intra correlations into the multivariate analysis. To select the optimal service composition, the proposed framework uses QoS time series' inter correlations and performs a novel time series group similarity approach on the predicted QoS values. Experiments are conducted on real QoS dataset and results prove the efficiency of the proposed approach.

23 May 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HCHanbo Cai
Hanbo Cai
PZPengcheng Zhang
Pengcheng Zhang
HDHai Dong
Hai Dong
YXYan Xiao
Yan Xiao
SKStefanos Koffas
Stefanos Koffas
YLYiming Li
Yiming Li
Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can implant malicious prediction behaviors into victim models by poisoning their training process. In this paper, we revisit poison-only backdoor attacks against speech recognition. We reveal that existing methods are not stealthy since their trigger patterns are perceptible to humans or machine detection. This limitation is mostly because their trigger patterns are simple noises or separable and distinctive clips. Motivated by these findings, we propose to exploit elements of sound ( e.g ., pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks. Specifically, we insert a short-duration high-pitched signal as the trigger and increase the pitch of remaining audio clips to ‘mask’ it for designing stealthy pitch-based triggers. We manipulate timbre features of victim audio to design the stealthy timbre-based attack and design a voiceprint selection module to facilitate the multi-backdoor attack. Our attacks can generate more ‘natural’ poisoned samples and therefore are more stealthy. Extensive experiments are conducted on benchmark datasets, which verify the effectiveness of our attacks under different settings ( e.g ., all-to-one, all-to-all, clean-label, physical, and multi-backdoor settings) and their stealthiness. Our methods achieve attack success rates of over 95% in most cases and are nearly undetectable. The code for reproducing main experiments are available at https://github.com/HanboCai/BadSpeech_SoE.