Deep Learning Attacks and Active Defences: A Cybersecurity Perspective

Funding: 2023: $64,840
2024: $213,918
2025: $203,852

Project Member(s): Liu, B., Liu, W.

Funding or Partner Organisation: Australian Research Council (ARC Discovery Projects)
Australian Research Council (ARC Discovery Projects)

Start year: 2023

Summary: The project aims to build a robust (resilient) deep learning system by analysing deep learning attacks in the context of cybersecurity attack life cycle to identify attacks in their early stages, using active defense methods to ensure efficient defense, and developing forensic strategies to prevent further attacks.

Publications:

Chen, H, Zhu, T, Liu, B, Zhou, W & Yu, PS 2024, 'Fine-tuning a Biased Model for Improving Fairness', IEEE Transactions on Big Data, pp. 1-15.
View/Download from: Publisher's site

Liu, B, Liu, B, Ding, M & Zhu, T 2024, 'MeST-Former: Motion-enhanced Spatiotemporal Transformer for generalizable Deepfake detection', Neurocomputing, vol. 610, pp. 128588-128588.
View/Download from: Publisher's site

Tian, H, Liu, B, Zhu, T, Zhou, W & Yu, PS 2024, 'Distilling Fair Representations From Fair Teachers', IEEE Transactions on Big Data, pp. 1-14.
View/Download from: Publisher's site

Tian, H, Liu, B, Zhu, T, Zhou, W & Yu, PS 2024, 'MultiFair: Model Fairness With Multiple Sensitive Attributes', IEEE Transactions on Neural Networks and Learning Systems, pp. 1-14.
View/Download from: Publisher's site

Zhang, G, Liu, B, Zhu, T, Ding, M & Zhou, W 2024, 'PPFed: A Privacy-Preserving and Personalized Federated Learning Framework', IEEE Internet of Things Journal, vol. 11, no. 11, pp. 19380-19393.
View/Download from: Publisher's site

Zhao, Y, Liu, B, Zhu, T, Ding, M, Yu, X & Zhou, W 2024, 'Proactive image manipulation detection via deep semi-fragile watermark', Neurocomputing, vol. 585, pp. 127593-127593.
View/Download from: Publisher's site

Liu, B, Liu, B, Ding, M & Zhu, T 1970, 'Detection of Diffusion Model-Generated Faces by Assessing Smoothness and Noise Tolerance', 2024 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), 2024 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), IEEE, pp. 1-6.
View/Download from: Publisher's site

Tian, H, Zhang, G, Liu, B, Zhu, T, Ding, M & Zhou, W 1970, 'When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks', Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}, International Joint Conferences on Artificial Intelligence Organization, pp. 512-520.
View/Download from: Publisher's site

Xu, Q, Du, H, Chen, H, Liu, B & Yu, X 1970, 'MMOOC: A Multimodal Misinformation Dataset for Out-of-Context News Analysis', Springer Nature Singapore, pp. 444-459.
View/Download from: Publisher's site

Zhang, G, Liu, B, Tian, H, Zhu, T, Ding, M & Zhou, W 1970, 'How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers', Proceedings of the 33rd USENIX Security Symposium, pp. 6795-6812.

Chivukula, AS, Yang, X, Liu, B, Liu, W & Zhou, W 2022, Adversarial Deep Learning in Cybersecurity Attack Taxonomies, Defence Mechanisms, and Learning Theories, Springer.

FOR Codes: Data and information privacy, Data security and protection, Cybersecurity

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.