4 papers
Efficient DP-SGD for LLMs with Randomized Clipping
Enayat Ullah, Sai Aparna Aketi, Devansh Gupta +2
Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, pr…
Edgeworth Accountant: An Analytical Approach to Differential Privacy Composition
Hua Wang, Sheng Gao, Huanyu Zhang +3
In privacy-preserving data analysis, many procedures and algorithms are structured as compositions of multiple private building blocks. As such, an important question is how to eff…
Statler: State-Maintaining Language Models for Embodied Reasoning
Takuma Yoneda, Jiading Fang, Peng Li +7
There has been a significant research interest in employing large language models to empower intelligent robots with complex reasoning. Existing work focuses on harnessing their ab…
Contraction of Locally Differentially Private Mechanisms
Shahab Asoodeh, Huanyu Zhang
We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between and outp…