182 citations · 625 across the 44 of their papers we have counts for
24 papers · 1 filter
Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation
Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang +2
Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, d…
2D-Shapley: A Framework for Fragmented Data Valuation
Zhihong Liu, Hoang Anh Just, Xiangyu Chang +2
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 mach…
Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources
Feiyang Kang, Hoang Anh Just, Anit Kumar Sahu +1
Traditionally, data selection has been studied in settings where all samples from prospective sources are fully revealed to a machine learning developer. However, in practical data…
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
Junyuan Hong, Yi Zeng, Shuyang Yu +3
Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access…
LAVA: Data Valuation without Pre-Specified Learning Algorithms
Hoang Anh Just, Feiyang Kang, Jiachen T. Wang +4
Traditionally, data valuation (DV) is posed as a problem of equitably splitting the validation performance of a learning algorithm among the training data. As a result, the calcula…
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms
Minzhou Pan, Yi Zeng, Lingjuan Lyu +2
Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised le…
On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds
Ming Jin, Vanshaj Khattar, Harshal Kaushik +2
We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension. The main results are: \emph{(1)} the class of…
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
Jiachen T. Wang, Ruoxi Jia
Data valuation has wide use cases in machine learning, including improving data quality and creating economic incentives for data sharing. This paper studies the robustness of data…
Label-Only Model Inversion Attacks via Boundary Repulsion
Mostafa Kahla, Si Chen, Hoang Anh Just +1
Recent studies show that the state-of-the-art deep neural networks are vulnerable to model inversion attacks, in which access to a model is abused to reconstruct private training d…
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…
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…
Knowledge-Enriched Distributional Model Inversion Attacks
Si Chen, Mostafa Kahla, Ruoxi Jia +1
Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a grow…
A Principled Approach to Data Valuation for Federated Learning
Tianhao Wang, Johannes Rausch, Ce Zhang +2
Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. In order to sustain long-term participation of data owners, it i…
Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy
Min Du, Ruoxi Jia, Dawn Song
Outlier detection and novelty detection are two important topics for anomaly detection. Suppose the majority of a dataset are drawn from a certain distribution, outlier detection a…
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei +3
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have r…
Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Ruoxi Jia, Fan Wu, Xuehui Sun +6
Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a…
Towards Efficient Data Valuation Based on the Shapley Value
Ruoxi Jia, David Dao, Boxin Wang +7
"How much is my data worth?" is an increasingly common question posed by organizations and individuals alike. An answer to this question could allow, for instance, fairly distribut…
One Bit Matters: Understanding Adversarial Examples as the Abuse of Redundancy
Jingkang Wang, Ruoxi Jia, Gerald Friedland +2
Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results…