no code implementations • 7 Apr 2024 • Bishwas Mandal, George Amariucai, Shuangqing Wei
Our approach entails prompting GPT-4 by transforming tabular data points into textual format, followed by the inclusion of precise sanitization instructions in a zero-shot manner.
no code implementations • 7 Apr 2024 • Bishwas Mandal, George Amariucai, Shuangqing Wei
Unlike previous studies that primarily focus on scenarios where all users share identical private and utility attributes and often rely on auxiliary datasets or manual annotations, we introduce a collaborative data-sharing mechanism between two user groups through a trusted third party.
1 code implementation • 27 Oct 2023 • Dong Qin, George Amariucai, Daji Qiao, Yong Guan, Shen Fu
While avoiding the artifacts problem, this new category suffers from the Encoding Prediction in the Explanation (EPITE) problem, in which the predictor's decisions rely not on the features, but on the masks that selects those features.
1 code implementation • 4 May 2022 • Bishwas Mandal, George Amariucai, Shuangqing Wei
We propose an adversarial learning framework that deals with the privacy-utility tradeoff problem under two types of conditions: data-type ignorant, and data-type aware.
no code implementations • 29 Sep 2021 • Bishwas Mandal, George Amariucai, Shuangqing Wei
The dynamic setting corresponds to the min-max two-player game whereas the constant setting corresponds to a generator which tries to outperform an adversary already trained using ground truth data.
no code implementations • 24 Feb 2020 • Abiola Osho, Caden Waters, George Amariucai
We show that the models for True and False message propagation differ significantly, both in the prediction parameters and in the message features that govern the diffusion.