1 code implementation • 18 Jun 2023 • Zhihong Liu, Hoang Anh Just, Xiangyu Chang, Xi Chen, Ruoxi Jia
Data valuation -- quantifying the contribution of individual data sources to certain predictive behaviors of a model -- is of great importance to enhancing the transparency of machine learning and designing incentive systems for data sharing.
1 code implementation • 28 Apr 2023 • Hoang Anh Just, Feiyang Kang, Jiachen T. Wang, Yi Zeng, Myeongseob Ko, Ming Jin, Ruoxi Jia
(1) We develop a proxy for the validation performance associated with a training set based on a non-conventional class-wise Wasserstein distance between training and validation sets.
2 code implementations • 11 Apr 2022 • Yi Zeng, Minzhou Pan, Hoang Anh Just, Lingjuan Lyu, Meikang Qiu, Ruoxi Jia
With poisoning equal to or less than 0. 5% of the target-class data and 0. 05% of the training set, we can train a model to classify test examples from arbitrary classes into the target class when the examples are patched with a backdoor trigger.
Ranked #1 on Clean-label Backdoor Attack (0.05%) on Tiny ImageNet
1 code implementation • CVPR 2022 • Mostafa Kahla, Si Chen, Hoang Anh Just, Ruoxi Jia
In this paper, we introduce an algorithm, Boundary-Repelling Model Inversion (BREP-MI), to invert private training data using only the target model's predicted labels.
1 code implementation • 24 Nov 2021 • Yingyan Zeng, Jiachen T. Wang, Si Chen, Hoang Anh Just, Ran Jin, Ruoxi Jia
In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model.