Junyuan "Jason" Hong

I am a joint postdoctoral fellow advised by Dr. Zhangyang Wang in the Institute for Foundations of Machine Learning (IFML) and Wireless Networking and Communications Group (WNCG), and also affiliated with the UT AI Health Lab as well as the Good System Challenge. I was recognized as one of the MLSys Rising Stars in 2024 and received a Best Paper Nomination at VLDB 2024. My work was covered by The White House, and MSU Office of Research and Innovation. Part of my work is funded by OpenAI Researcher Access Program.

Publications

DeepOSets: Non-Autoregressive In-Context Learning of Supervised Learning Operators

DeepOSets: Non-Autoregressive In-Context Learning of Supervised Learning Operators

Shao-Ting Chiu, Junyuan Hong, U. Braga-Neto

arXiv.org 2024

FedKDD: International Joint Workshop on Federated Learning for Data Mining and Graph Analytics

Junyuan Hong, Carl Yang, Zhuangdi Zhu, Zheng Xu, Nathalie Baracaldo, Neil Shah, A. Avestimehr, Jiayu Zhou

Knowledge Discovery and Data Mining 2024

LLM-PBE: Assessing Data Privacy in Large Language Models

LLM-PBE: Assessing Data Privacy in Large Language Models

Qinbin Li, Junyuan Hong, Chulin Xie, Jeffrey Tan, Rachel Xin, Junyi Hou, Xavier Yin, Zhun Wang, Dan Hendrycks, Zhangyang Wang, Bo Li, Bingsheng He, Dawn Song

Proceedings of the VLDB Endowment 2024

GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Zhen Xiang, Linzhi Zheng, Yanjie Li, Junyuan Hong, Qinbin Li, Han Xie, Jiawei Zhang, Zidi Xiong, Chulin Xie, Carl Yang, Dawn Song, Bo Li

arXiv.org 2024

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian Bartoldson, A. Jaiswal, Kaidi Xu, B. Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, Bo Li

International Conference on Machine Learning 2024

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk

Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang

2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2024

On the Generalization Ability of Unsupervised Pretraining

On the Generalization Ability of Unsupervised Pretraining

Yuyang Deng, Junyuan Hong, Jiayu Zhou, M. Mahdavi

International Conference on Artificial Intelligence and Statistics 2024

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen

International Conference on Machine Learning 2024

Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning

Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning

Shuyang Yu, Junyuan Hong, Yi Zeng, Fei Wang, Ruoxi Jia, Jiayu Zhou

arXiv.org 2023

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang

International Conference on Learning Representations 2023

Understanding Deep Gradient Leakage via Inversion Influence Functions

Understanding Deep Gradient Leakage via Inversion Influence Functions

Haobo Zhang, Junyuan Hong, Yuyang Deng, M. Mahdavi, Jiayu Zhou

Neural Information Processing Systems 2023

Safe and Robust Watermark Injection with a Single OoD Image

Safe and Robust Watermark Injection with a Single OoD Image

Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou

International Conference on Learning Representations 2023

International Workshop on Federated Learning for Distributed Data Mining

Junyuan Hong, Zhuangdi Zhu, Lingjuan Lyu, Yang Zhou, Vishnu Naresh Boddeti, Jiayu Zhou

Knowledge Discovery and Data Mining 2023

FedNoisy: Federated Noisy Label Learning Benchmark

FedNoisy: Federated Noisy Label Learning Benchmark

Siqi Liang, Jintao Huang, Dun Zeng, Junyuan Hong, Jiayu Zhou, Zenglin Xu

arXiv.org 2023

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Junyuan Hong, Yi Zeng, Shuyang Yu, L. Lyu, R. Jia, Jiayu Zhou

International Conference on Machine Learning 2023

On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space

On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space

Yuyang Deng, Nidham Gazagnadou, Junyuan Hong, M. Mahdavi, L. Lyu

arXiv.org 2023

A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection

A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection

Haobo Zhang, Junyuan Hong, Fan Dong, S. Drew, Liangjie Xue, Jiayu Zhou

arXiv.org 2023

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, M. Spranger

Neural Information Processing Systems 2022

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang

Neural Information Processing Systems 2022

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts

Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang

Trans. Mach. Learn. Res. 2022

Resilient and Communication Efficient Learning for Heterogeneous Federated Systems

Resilient and Communication Efficient Learning for Heterogeneous Federated Systems

Zhuangdi Zhu, Junyuan Hong, S. Drew, Jiayu Zhou

International Conference on Machine Learning 2022

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

International Conference on Learning Representations 2022

Federated Adversarial Debiasing for Fair and Transferable Representations

Federated Adversarial Debiasing for Fair and Transferable Representations

Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, H. Dodge, Jiayu Zhou

Knowledge Discovery and Data Mining 2021

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

AAAI Conference on Artificial Intelligence 2021

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou

International Conference on Machine Learning 2021

Learning Model-Based Privacy Protection under Budget Constraints

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

AAAI Conference on Artificial Intelligence 2021

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent

Junyuan Hong, Zhangyang Wang, Jiayu Zhou

Conference on Fairness, Accountability and Transparency 2021

Detecting MCI using real‐time, ecologically valid data capture methodology: How to improve scientific rigor in digital biomarker analyses

Junyuan Hong, J. Kaye, H. Dodge, Jiayu Zhou

Variant Grassmann Manifolds

Variant Grassmann Manifolds

Junyuan Hong, Yang Li, Huanhuan Chen

ACM Transactions on Knowledge Discovery from Data 2019

Short Sequence Classification Through Discriminable Linear Dynamical System

Short Sequence Classification Through Discriminable Linear Dynamical System

Yang Li, Junyuan Hong, Huanhuan Chen

IEEE Transactions on Neural Networks and Learning Systems 2019

Disturbance Grassmann Kernels for Subspace-Based Learning

Disturbance Grassmann Kernels for Subspace-Based Learning

Junyuan Hong, Huanhuan Chen, Feng Lin

Knowledge Discovery and Data Mining 2018

Sequential Data Classification in the Space of Liquid State Machines

Y. Li, Junyuan Hong, Huanhuan Chen

ECML/PKDD 2016

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

Shuyang Yu, Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

International Conference on Learning Representations 2023

MECTA: Memory-Economic Continual Test-Time Model Adaptation

MECTA: Memory-Economic Continual Test-Time Model Adaptation

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

International Conference on Learning Representations 2023

On Dynamic Noise Influence in Differentially Private Learning

Junyuan Hong, Zhangyang Wang, Jiayu Zhou

arXiv.org 2021

Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning

Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

arXiv.org 2021