2025-01-14-li25a.md

title	booktitle	year	volume	series	month	publisher	pdf	url	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
Differentially Private Deep Learning with Importance-based Adaptive Gradient Processing	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/li25a/li25a.pdf	https://proceedings.mlr.press/v260/li25a.html	JMWJjg0FXe	In recent years, with the rapid development of neural network technology, the application of deep learning in the field of artificial intelligence has made significant progress and improvement. However, during the training of neural network models, the utilization of datasets is involved, and these datasets may contain sensitive information from users. Attackers might exploit the well-trained models to gain access to this sensitive information, leading to privacy breaches. Considering this risk, some deep learning algorithms incorporate differential privacy technology to safeguard the privacy of the trained model. This protection comes at the cost of certain model performance, achieved by adding controllable random noise. In this paper, we propose a differential privacy deep learning algorithm based on the importance of each layer’s gradients, called DP-AdamILG. DP-AdamILG further mitigates the impact of noise addition on model performance. It accomplishes this by combining the dynamic privacy budget allocation strategy with the formation of noise gradients based on the importance of each layer’s gradients. And the algorithm’s privacy is theoretically proven. Experimental results show that the DP-AdamILG algorithm can reach good performance of the neural network model and show strong robustness.	inproceedings	2640-3498	li25a	Differentially Private Deep Learning with Importance-based Adaptive Gradient Processing	159	174	159-174	159	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Li, Ping and Liang, Mingwei and Jiang, Zhao and Zhang, Jun	given family Ping Li given family Mingwei Liang given family Zhao Jiang given family Jun Zhang	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14