7 papers
Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering
Xincheng Xu, Thilina Ranbaduge, Qing Wang +2
Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privac…
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
Yashothara Shanmugarasa, Ming Ding, M. A. P Chamikara +1
Large language models (LLMs) are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer signific…
Privacy Meets Explainability: Managing Confidential Data and Transparency Policies in LLM-Empowered Science
Yashothara Shanmugarasa, Shidong Pan, Ming Ding +2
As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explor…
Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Data
Kanishka Ranaweera, Dinh C. Nguyen, Pubudu N. Pathirana +4
In the era of data-driven machine-learning applications, privacy concerns and the scarcity of labeled data have become paramount challenges. These challenges are particularly prono…
Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning
Kanishka Ranaweera, David Smith, Pubudu N. Pathirana +3
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine lear…
Federated Learning with Differential Privacy: An Utility-Enhanced Approach
Kanishka Ranaweera, Dinh C. Nguyen, Pubudu N. Pathirana +4
Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with…