NhatHai Phan

Active Membership Inference Attack under Local Differential Privacy in Federated Learning

2023 · arXiv (Cornell University)

Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership inference (AMI) attack carried …

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation

2025 · arXiv (Cornell University)

Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training. This creates a tension: how do watermark-induced shifts interact …