9 papers
DP-SAPF: Saliency-Aware Parameter Fine-tuning of Public Models for Differentially Private Image Synthesis
Chen Gong, Kecen Li, Zinan Lin +1
Differentially private (DP) image synthesis generates images that preserve the statistical characteristics of a sensitive dataset, enabling sensitive data analysis and usage while…
Differentially Private Contrastive Learning via Bounding Group-level Contribution
Kecen Li, Chen Gong, Zinan Lin +2
Differentially private (DP) contrastive learning aims to learn general-purpose representations from sensitive data, alleviating the privacy leakage concerns of organizations deploy…
PrivCode: When Code Generation Meets Differential Privacy
Zheng Liu, Chen Gong, Terry Yue Zhuo +4
Large language models (LLMs) have presented outstanding performance in code generation and completion. However, fine-tuning these models on private datasets can raise privacy and p…
From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum
Chen Gong, Kecen Li, Zinan Lin +1
To improve the quality of Differentially private (DP) synthetic images, most studies have focused on improving the core optimization techniques (e.g., DP-SGD). Recently, we have wi…
PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
Chen Gong, Zheng Liu, Kecen Li +1
Recently, offline reinforcement learning (RL) has become a popular RL paradigm. In offline RL, data providers share pre-collected datasets -- either as individual transitions or se…
Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis
Kai Chen, Chen Gong, Tianhao Wang
In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this concl…