In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
To alleviate the utility degradation of deep learning image classification with differential
privacy (DP) employing extra public data or pre-trained models has been widely explored …
privacy (DP) employing extra public data or pre-trained models has been widely explored …
Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
Differentially private SGD (DP-SGD) holds the promise of enabling the safe and responsible
application of machine learning to sensitive datasets. However, DP-SGD only provides a …
application of machine learning to sensitive datasets. However, DP-SGD only provides a …
DP-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization
Federated learning (FL) is a distributed machine learning approach that allows multiple
clients to collaboratively train a model without sharing their raw data. To prevent sensitive …
clients to collaboratively train a model without sharing their raw data. To prevent sensitive …
Mitigating and Understanding the Security and Privacy Risks in AI Systems
R Zhu - 2024 - search.proquest.com
The rapid advancement of AI technologies has brought forth significant security and privacy
challenges, affecting various sectors including healthcare, finance, and autonomous …
challenges, affecting various sectors including healthcare, finance, and autonomous …
Improving Private Training via In-distribution Public Data Synthesis and Generalization
J Park, Y Choi, J Lee - openreview.net
To alleviate the utility degradation of deep learning classification with differential privacy
(DP), employing extra public data or pre-trained models has been widely explored …
(DP), employing extra public data or pre-trained models has been widely explored …