b'Ruoxi Jia'

research

∙ 08/30/2023

Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation

Data valuation, a critical aspect of data-centric ML research, aims to q...

0 Jiachen T. Wang, et al. ∙

research

∙ 08/20/2023

Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models

Current literature, aiming to surpass the "Chain-of-Thought" approach, o...

0 Bilgehan Sel, et al. ∙

research

∙ 06/18/2023

2D-Shapley: A Framework for Fragmented Data Valuation

Data valuation – quantifying the contribution of individual data sources...

0 Zhihong Liu, et al. ∙

research

∙ 06/04/2023

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Data-free knowledge distillation (KD) helps transfer knowledge from a pr...

0 Junyuan Hong, et al. ∙

research

∙ 04/28/2023

LAVA: Data Valuation without Pre-Specified Learning Algorithms

Traditionally, data valuation is posed as a problem of equitably splitti...

4 Hoang Anh Just, et al. ∙

research

∙ 04/09/2023

A Note on "Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms"

Data valuation is a growing research field that studies the influence of...

0 Jiachen T. Wang, et al. ∙

research

∙ 02/22/2023

A Note on "Towards Efficient Data Valuation Based on the Shapley Value”

The Shapley value (SV) has emerged as a promising method for data valuat...

0 Jiachen T. Wang, et al. ∙

research

∙ 02/22/2023

ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms

Backdoor data detection is traditionally studied in an end-to-end superv...

6 Minzhou Pan, et al. ∙

research

∙ 12/02/2022

On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds

We study the expressibility and learnability of convex optimization solu...

0 Ming Jin, et al. ∙

research

∙ 10/30/2022

Robust Data Valuation via Variance Reduced Data Shapley

Data valuation, especially quantifying data value in algorithmic predict...

0 Mengmeng Wu, et al. ∙

research

∙ 10/17/2022

Private Data Valuation and Fair Payment in Data Marketplaces

Data valuation is an essential task in a data marketplace. It aims at fa...

0 Zhihua Tian, et al. ∙

research

∙ 10/12/2022

How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?

Given the volume of data needed to train modern machine learning models,...

25 Yi Zeng, et al. ∙

research

∙ 09/19/2022

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

Previous works have validated that text generation APIs can be stolen th...

0 Xuanli He, et al. ∙

research

∙ 06/14/2022

Turning a Curse Into a Blessing: Enabling Clean-Data-Free Defenses by Model Inversion

It is becoming increasingly common to utilize pre-trained models provide...

7 Si Chen, et al. ∙

research

∙ 05/30/2022

Data Banzhaf: A Data Valuation Framework with Maximal Robustness to Learning Stochasticity

This paper studies the robustness of data valuation to noisy model perfo...

6 Tianhao Wang, et al. ∙

research

∙ 04/15/2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

With the increasing adoption of NLP models in real-world products, it be...

0 Weiyan Shi, et al. ∙

research

∙ 04/11/2022

Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information

Backdoor attacks insert malicious data into a training set so that, duri...

13 Yi Zeng, et al. ∙

research

∙ 03/03/2022

Label-Only Model Inversion Attacks via Boundary Repulsion

Recent studies show that the state-of-the-art deep neural networks are v...

0 Mostafa Kahla, et al. ∙

research

∙ 11/24/2021

Learning to Refit for Convex Learning Problems

Machine learning (ML) models need to be frequently retrained on changing...

0 Yingyan Zeng, et al. ∙

research

∙ 10/07/2021

Adversarial Unlearning of Backdoors via Implicit Hypergradient

We propose a minimax formulation for removing backdoors from a given poi...

0 Yi Zeng, et al. ∙

research

∙ 08/30/2021

Selective Differential Privacy for Language Modeling

With the increasing adoption of language models in applications involvin...

0 Weiyan Shi, et al. ∙

research

∙ 07/14/2021

Zero-Round Active Learning

Active learning (AL) aims at reducing labeling effort by identifying the...

0 Si Chen, et al. ∙

research

∙ 07/13/2021

Learnability of Learning Performance and Its Application to Data Valuation

For most machine learning (ML) tasks, evaluating learning performance on...

1 Tianhao Wang, et al. ∙

research

∙ 06/10/2021

A Unified Framework for Task-Driven Data Quality Management

High-quality data is critical to train performant Machine Learning (ML) ...

0 Tianhao Wang, et al. ∙

research

∙ 04/23/2021

One-Round Active Learning

Active learning has been a main solution for reducing data labeling cost...

0 Tianhao Wang, et al. ∙

research

∙ 04/07/2021

Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective

Backdoor attacks have been considered a severe security threat to deep l...

5 Yi Zeng, et al. ∙

research

∙ 03/02/2021

DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing

Deep learning techniques have achieved remarkable performance in wide-ra...

0 Wenxiao Wang, et al. ∙

research

∙ 10/08/2020

Improved Techniques for Model Inversion Attacks

Model inversion (MI) attacks in the whitebox setting are aimed at recons...

0 Si Chen, et al. ∙

research

∙ 10/05/2020

InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Large-scale language models such as BERT have achieved state-of-the-art ...

0 Boxin Wang, et al. ∙

research

∙ 09/14/2020

A Principled Approach to Data Valuation for Federated Learning

Federated learning (FL) is a popular technique to train machine learning...

25 Tianhao Wang, et al. ∙

research

∙ 09/11/2020

Improving Robustness to Model Inversion Attacks via Mutual Information Regularization

This paper studies defense mechanisms against model inversion (MI) attac...

0 Tianhao Wang, et al. ∙

research

∙ 06/22/2020

Private Distributed Mean Estimation

Ever since its proposal, differential privacy has become the golden stan...

0 Lun Wang, et al. ∙

research

∙ 11/17/2019

REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data

Deep neural networks (DNNs) have achieved tremendous success in various ...

0 Xinyun Chen, et al. ∙

research

∙ 11/17/2019

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

This paper studies model-inversion attacks, in which the access to a mod...

6 Yuheng Zhang, et al. ∙

research

∙ 11/17/2019

An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms

This paper focuses on valuating training data for supervised learning ta...

14 Ruoxi Jia, et al. ∙

research

∙ 11/16/2019

Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy

Outlier detection and novelty detection are two important topics for ano...

14 Min Du, et al. ∙

research

∙ 08/22/2019

Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms

Given a data set D containing millions of data points and a data consume...

11 Ruoxi Jia, et al. ∙

research

∙ 02/27/2019

Towards Efficient Data Valuation Based on the Shapley Value

"How much is my data worth?" is an increasingly common question posed by...

17 Ruoxi Jia, et al. ∙

research

∙ 10/23/2018

One Bit Matters: Understanding Adversarial Examples as the Abuse of Redundancy

Despite the great success achieved in machine learning (ML), adversarial...

0 Ruoxi Jia, et al. ∙

research

∙ 07/10/2018

The Helmholtz Method: Using Perceptual Compression to Reduce Machine Learning Complexity

This paper proposes a fundamental answer to a frequently asked question ...

0 Gerald Friedland, et al. ∙

research

∙ 06/22/2014

Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation

We present results from a set of experiments in this pilot study to inve...

0 Ming Jin, et al. ∙

Ruoxi Jia

Featured Co-authors