Bingqian Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bingqian Du has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chuan Wu
The University of Hong Kong, Hong Kong, China
2 shared publications - Bin Yuan
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Boyu Zhang
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China
1 shared publication - Di Yuan
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Le Fang
School of Design, The Hong Kong Polytechnic University, Hong Kong SAR, China
1 shared publication - Liyao Xiang
Shanghai Jiao Tong University
1 shared publication
Latest Publications
- Open Access
- 30 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Modeling and Performance Evaluation of Computing Systems
- Vol. 10 (2) , 1-25
Mitigating Unfairness in Differentially-Private Federated Learning
Federated learning is a new learning paradigm which utilizes crowdsourced data stored at dispersed user devices (aka clients) to learn a global model. Studies have shown that even though data are kept on local devices, an adversary is still able to infer client information during the training process or from the learned model. Differential privacy has recently been introduced to deep learning model training, to protect data privacy of clients. Nonetheless, it exacerbates unfairness with the learned model among participating clients due to its uniform clipping and noise addition, even when the training loss function explicitly considers unfairness. To validate the impact of the differential privacy mechanism in federated learning, we carefully approximate the correlation between fairness performance across clients and the fundamental operations within the differential privacy mechanism and quantify the influence of differential privacy mechanisms on model performance across various clients. Subsequently, leveraging our theoretical findings regarding the effect of the differential privacy mechanism, we formulate the unfairness mitigation problem and propose an algorithm based on the modified method of differential multipliers. Extensive evaluation shows that our method outperforms state-of-the-art differentially private federated learning algorithm by about 30% for non-i.i.d. data distribution in terms of the variance of model performance across clients.
- 30 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Modeling and Performance Evaluation of Computing Systems
- Vol. 10 (2) , 1-25
Open AccessMitigating Unfairness in Differentially-Private Federated Learning
Federated learning is a new learning paradigm which utilizes crowdsourced data stored at dispersed user devices (aka clients) to learn a global model. Studies have shown that even though data are kept on local devices, an adversary is still able to infer client information during the training process or from the learned model. Differential privacy has recently been introduced to deep learning model training, to protect data privacy of clients. Nonetheless, it exacerbates unfairness with the learned model among participating clients due to its uniform clipping and noise addition, even when the training loss function explicitly considers unfairness. To validate the impact of the differential privacy mechanism in federated learning, we carefully approximate the correlation between fairness performance across clients and the fundamental operations within the differential privacy mechanism and quantify the influence of differential privacy mechanisms on model performance across various clients. Subsequently, leveraging our theoretical findings regarding the effect of the differential privacy mechanism, we formulate the unfairness mitigation problem and propose an algorithm based on the modified method of differential multipliers. Extensive evaluation shows that our method outperforms state-of-the-art differentially private federated learning algorithm by about 30% for non-i.i.d. data distribution in terms of the variance of model performance across clients.
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1256-1270
Membership Inference Attacks against Vision Transformers: Mosaic MixUp Training to the Defense
Vision transformers (ViTs) have demonstrated great success in various fundamental CV tasks, mainly benefiting from their self-attention-based transformer architectures, and the paradigm of pre-training followed by fine-tuning. However, such advantages may lead to significant data privacy risks, such as membership inference attacks (MIAs), which remain unclear. This paper presents the first comprehensive study on MIAs and corresponding defenses against ViTs. Our first contribution is a rollout-attention-based MIA method (RAMIA), based on an experimental observation that the attention, more precisely the rollout attention, behaves disproportionately for members and non-members. We evaluate RAMIA on the standard ViT architecture proposed by Google (ICLR 2021), achieving high accuracy, precision, and recall performance. Further, inspired by another experimental observation on a strong connection between positional embeddings (PEs) and attentions, we propose a novel framework for training ViTs, named Mosaic MixUp Training (MMUT), as a defense against RAMIA. Intuitively, MMUT mixes up private images and public ones at a patch level, and mosaics the corresponding PEs with a global learnable mosaic embedding. Our empirical results show MMUT achieves a much better accuracy-privacy trade-off than some common defense mechanisms. Extensive experiments are conducted to rigorously evaluate both RAMIA and MMUT.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1256-1270
Open AccessMembership Inference Attacks against Vision Transformers: Mosaic MixUp Training to the Defense
Vision transformers (ViTs) have demonstrated great success in various fundamental CV tasks, mainly benefiting from their self-attention-based transformer architectures, and the paradigm of pre-training followed by fine-tuning. However, such advantages may lead to significant data privacy risks, such as membership inference attacks (MIAs), which remain unclear. This paper presents the first comprehensive study on MIAs and corresponding defenses against ViTs. Our first contribution is a rollout-attention-based MIA method (RAMIA), based on an experimental observation that the attention, more precisely the rollout attention, behaves disproportionately for members and non-members. We evaluate RAMIA on the standard ViT architecture proposed by Google (ICLR 2021), achieving high accuracy, precision, and recall performance. Further, inspired by another experimental observation on a strong connection between positional embeddings (PEs) and attentions, we propose a novel framework for training ViTs, named Mosaic MixUp Training (MMUT), as a defense against RAMIA. Intuitively, MMUT mixes up private images and public ones at a patch level, and mosaics the corresponding PEs with a global learnable mosaic embedding. Our empirical results show MMUT achieves a much better accuracy-privacy trade-off than some common defense mechanisms. Extensive experiments are conducted to rigorously evaluate both RAMIA and MMUT.
- 18 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 250
Differentially private recommender system with variational autoencoders
- 18 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 250
Differentially private recommender system with variational autoencoders