182 citations · 625 across the 44 of their papers we have counts for
9 papers · 1 filter
ModelPred: A Framework for Predicting Trained Model from Training Data
Yingyan Zeng, Jiachen T. Wang, Si Chen +3
In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various s…
Adversarial Unlearning of Backdoors via Implicit Hypergradient
Yi Zeng, Si Chen, Won Park +3
We propose a minimax formulation for removing backdoors from a given poisoned model based on a small set of clean data. This formulation encompasses much of prior work on backdoor…
Zero-Round Active Learning
Si Chen, Tianhao Wang, Ruoxi Jia
Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: Firs…
Selective Differential Privacy for Language Modeling
Weiyan Shi, Aiqi Cui, Evan Li +2
With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this chal…
Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning
Tianhao Wang, Yu Yang, Ruoxi Jia
The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems. Both methods have recently been proposed as a principled…
A Unified Framework for Task-Driven Data Quality Management
Tianhao Wang, Yi Zeng, Ming Jin +1
High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM). Existing DQM schemes often cannot sati…
One-Round Active Learning
Tianhao Wang, Si Chen, Ruoxi Jia
In this work, we initiate the study of one-round active learning, which aims to select a subset of unlabeled data points that achieve the highest model performance after being labe…
Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective
Yi Zeng, Won Park, Z. Morley Mao +1
Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain…
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Wenxiao Wang, Tianhao Wang, Lun Wang +4
Deep learning techniques have achieved remarkable performance in wide-ranging tasks. However, when trained on privacy-sensitive datasets, the model parameters may expose private in…