4 papers
ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
Atefeh Gilani, Sajani Vithana, Carol Xuan Long +3
Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM…
Reveal-or-Obscure: A Differentially Private Sampling Algorithm for Discrete Distributions
Naima Tasnim, Atefeh Gilani, Lalitha Sankar +1
We introduce a differentially private (DP) algorithm called reveal-or-obscure (ROO) to generate a single representative sample from a dataset of observations drawn i.i.d. from…
GeoClip: Geometry-Aware Clipping for Differentially Private SGD
Atefeh Gilani, Naima Tasnim, Lalitha Sankar +1
Differentially private stochastic gradient descent (DP-SGD) is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in…
Optimizing Noise Distributions for Differential Privacy
Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh +3
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP…