49 citations · 175 across the 19 of their papers we have counts for
20 papers
Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection
Jun Nie, Yonggang Zhang, Tongliang Liu +3
Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, l…
FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
Tian Wen, Zhiqin Yang, Yonggang Zhang +4
Federated learning (FL) suffers from performance degradation due to the inevitable presence of noisy annotations in distributed scenarios. Existing approaches have advanced in dist…
Detecting Generated Images by Fitting Natural Image Distributions
Yonggang Zhang, Jun Nie, Xinmei Tian +3
The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on t…
Epistemic Uncertainty for Generated Image Detection
Jun Nie, Yonggang Zhang, Tongliang Liu +3
We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key…
Revisiting Privacy-Utility Trade-off for DP Training with Pre-existing Knowledge
Yu Zheng, Wenchao Zhang, Yonggang Zhang +5
Differential privacy (DP) provides a provable framework for protecting individuals by customizing a random mechanism over a privacy-sensitive dataset. Deep learning models have dem…
FedImpro: Measuring and Improving Client Update in Federated Learning
Zhenheng Tang, Yonggang Zhang, Shaohuai Shi +4
Federated Learning (FL) models often experience client drift caused by heterogeneous data, where the distribution of data differs across clients. To address this issue, advanced re…
Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
Rong Dai, Yonggang Zhang, Ang Li +3
One-shot Federated Learning (OFL) has become a promising learning paradigm, enabling the training of a global server model via a single communication round. In OFL, the server mode…
Robust Training of Federated Models with Extremely Label Deficiency
Yonggang Zhang, Zhiqin Yang, Xinmei Tian +3
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency. Adva…
Federated Learning with Extremely Noisy Clients via Negative Distillation
Yang Lu, Lin Chen, Yonggang Zhang +4
Federated learning (FL) has shown remarkable success in cooperatively training deep models, while typically struggling with noisy labels. Advanced works propose to tackle label noi…
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Zhiqin Yang, Yonggang Zhang, Yu Zheng +4
Federated learning (FL) typically faces data heterogeneity, i.e., distribution shifting among clients. Sharing clients' information has shown great potentiality in mitigating data…
Moderately Distributional Exploration for Domain Generalization
Rui Dai, Yonggang Zhang, Zhen Fang +2
Domain generalization (DG) aims to tackle the distribution shift between training domains and unknown target domains. Generating new domains is one of the most effective approaches…
Hard Sample Matters a Lot in Zero-Shot Quantization
Huantong Li, Xiangmiao Wu, Fanbing Lv +5
Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network q…
Watermarking for Out-of-distribution Detection
Qizhou Wang, Feng Liu, Yonggang Zhang +4
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogr…
Towards Lightweight Black-Box Attacks against Deep Neural Networks
Chenghao Sun, Yonggang Zhang, Wan Chaoqun +5
Black-box attacks can generate adversarial examples without accessing the parameters of target model, largely exacerbating the threats of deployed deep neural networks (DNNs). Howe…
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning
Zhenheng Tang, Yonggang Zhang, Shaohuai Shi +3
In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a…
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Yongqiang Chen, Kaiwen Zhou, Yatao Bian +8
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data. Most efforts are devoted to advancin…
Prompt Distribution Learning
Yuning Lu, Jianzhuang Liu, Yonggang Zhang +2
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias pr…
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Yongqiang Chen, Han Yang, Yonggang Zhang +4
Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of m…
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Yongqiang Chen, Yonggang Zhang, Yatao Bian +6
Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.g., images), studies on graph data are still limited. Dif…
CausalAdv: Adversarial Robustness through the Lens of Causality
Yonggang Zhang, Mingming Gong, Tongliang Liu +5
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning. As causal reasoning has an instinct for modelling distribution change…