Junyuan Hong

Postdoctoral Fellow

IFML & WNCG at UT Austin

I am a postdoctoral fellow advised by Dr. Zhangyang Wang at the Institute for Foundations of Machine Learning (IFML) and the Wireless Networking and Communications Group (WNCG) at UT Austin. I obtained my Ph.D. in Computer Science and Engineering from Michigan State University, where I was advised by Dr. Jiayu Zhou. I hold a B.S. in Physics and an M.S. in Computer Science from the University of Science and Technology of China. I was honored as one of the MLCommons Rising Stars in 2024.

My long-term research vision is to establish Holistic Trustworthy AI for Healthcare. My recent research is driven by the emergent challenges in AI for Dementia Healthcare, and centers around Privacy-Centric Trustworthy Machine Learning toward Responsible AI where I pursue fairness, robustness, security and inclusiveness under privacy constraints. Most of my work (including GenAI GAI) follows these principles to trade-off efficiency, utility and privacy: edge-edge (federated learning) FL and edge-cloud (pre-training fine-tuning, transfer learning) EC collaboration.

Dementia [Healthcare] ⨉ Generative AI:
- Disease modeling and from distributed devicesFL.
- Conversational AI for dementia simulation and prevention GAI.
[Privacy] ⨉ Collaborative ML ⨉ Large Vision/Language Models:
- Tools: Efficient auditing tools, and adaptive private learning.
- Foundation Models: Privacy risks of diffusion modelsEC and private offsite prompt tuning of ChatGPTEC GAI.
- Applications for distributed vision, finance and disease modeling.
[Trustworthy ML] ⨉ Privacy:
- Benchmark the multi-dimensional trustworthiness of compressed LLMs GAI.
- AI Safety via automatic guardrail GAI.
- Fair unsupervised trainingEC and multi-group learningFL.
- Robustness acquired from collaboration, against adversarial samplesFL and OoD inferenceFL.
- Security in data-free distillationFL and model copyrightEC.
- Inclusive efficient system for for low-end devices by offsite prompt tuningECGAI, on-device model adaptationEC, private outsourcing trainingEC and customizable modelsFL.

Check my curricula vitae and feel free to drop me an email if you are interested in collaboration.

News

July, 2024 👥 We are exciting to organize the GenAI for Health: Potential, Trust and Policy Compliance workshop (GenAI4Health 2024) at NeurIPS 2024.
June, 2024 📊 New benchmark on LLM privacy is accepted to VLDB!
June, 2024 New paper on safeguarding LLM agent is online!
June, 2024 🏁 Thrilled to co-organize The LLM and Agent Safety Competition 2024 at NeurIPS 2024!
June, 2024 🌟 Grateful to receive API grants from the OpenAI’s Researcher Access Program!
May, 2024 🏁 Thrilled to co-organize The NeurIPS 2024 LLM Privacy Challenge! Join us for the competition!
May, 2024 🌟 I am honored to be selected one of ML and Systems Rising Stars by ML Commons for my work in health and trustworthy ML, 2024!
May, 2024 🎉 Two benchmark papers are accepted at ICML 2024: how to obtain trustworthy compressed LLMs (models at huggingface) and how to optimize LLMs with less memory.
April, 2024 🎤 I am honored to give a invited talk on conversational AI for dementia health at UT school of information.
March, 2024 🎤 I am honored to give a talk on the new privacy risk of GenAI at UT Good System Symposium 2024.
March, 2024 We are exciting to organize the International Joint Workshop on Federated Learning for Data Mining and Graph Analytics (FedKDD 2024).

March, 2024 Our benchmark work, Decoding Compressed Trust, has been accepted to SET LLM @ICLR. A curated set of compressed models are available at huggingface.
Feb, 2024 New benchmark preprint on zeroth-order optimization for LLMs.
Jan, 2024 🎉 Three papers are accepted: The first local privacy-preserving prompt tuning as Spotlight at ICLR, robust watermarking from one image as poster at ICLR, the generalization of unsupervised pretraining at AISTATS!
Dec, 2023 🍾 Our paper on amplifying privacy risks via fine-tuning (Shake-To-Leak) is accepted to SaTML.
Nov, 2023 🏅 Grateful to be selected as Top Reviewer at NeurIPS 2023.
Dec, 2023 Our new preprint on private prompt engineering for close-source LLMs is online.
Dec, 2023 ✈️ 🎷 I will be at New Orleans for presenting our recent work on understanding gradient privacy (NeurIPS'23 ) and tracking IP leakage in FL (NeurIPS-RegML).
Nov, 2023 🤖 We are releasing a set of compressed LLMs at compressed-llm for public benchmarks.
Nov, 2023 Our work on tracking IP leakage in FL is accepted to NeurIPS'23 Workshop on Regulated ML (NeurIPS-RegML).
Sep, 2023 Our work on understanding gradient privacy via inversion influence functions is accepted to NeurIPS'23.
Sep, 2023 Our new work on watermarking models using one image is online.
August, 2023 👥 We are organizing a KDD workshop on federated learning for distributed data mining (FL4Data-Mining) on August 7th at Long Beach🌴.
July, 2023 I am going to travel for ICML 2023 at Hawaii 🌺. Come and talk to me about data-free backdoor!
July, 2023 🏅 Honored to receive Research Enhancement Award for organizing FL4DataMining workshop! Thank you to MSU Graduate School!
July, 2023 🎓 I successfully defended my thesis. Many thanks to my collaborators, advisor and committees.
May, 2023 My new website is online with released junyuan-academic-theme including many cool new features.
April, 2023 One paper on data-free backdoor got accepted to ICML'23.
March, 2023 🏆 Our ILLIDAN Lab team just won the 3rd place in the U.S. PETs prize challenge. Media cover by The White House, MSU EGR news and MSU Office of Research and Innovation.
Jan, 2022 Two papers got accepted to ICLR'23: OoD detection by FL (splotlight!), memory-efficient CTA.
Sep, 2022 Our work on federated robustness sharing has been accepted to AAAI'23 (oral).
Nov, 2022 Two papers got accepted to NeurIPS'22: outsourcing training, backdoor defense.
May, 2022 Our work on connection-resilient FL got accepted to ICML'22.

Interests

Healthcare
Privacy
Trustworthy Machine Learning
Federated Learning
Large Language/Vision Models

Education

PhD in CSE, 2023

Michigan State University
MSc in Computer Science, 2018

University of Science and Technology of China
BSc in Physics, minor in CS., 2015

University of Science and Technology of China

Projects

DiRP Trustworthy LLM

Directed Reading Program (DiRP) on trustworthy large language models.

Holistic Trustworthy ML

Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.

Federated Learning

On the need of data privacy and more data, we strive to join the knowledge from a fair amount of users to train powerful deep neural networks without sharing data.

Privacy in Collaborative ML

On the concern of data privacy, we aim to develop algorithms towards learning accurate models privately from data.

AI for Dementia Healthcare

We aim to early detect and intervene dementia diseases leveraging the power of (Generative) AI.

Subspace Learning

Supervised learning on subspace data which could model real data like skeleton motion.

Publications

VLDB 2024 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.

ArXiv 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.

ICML 2024 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, Ajay Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song., Zhangyang Wang, Bo Li.

ICML 2024 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.

LLM Agents 2024 A-CONECT: Designing AI-based Conversational Chatbot for Early Dementia Intervention.
Junyuan Hong, Wenqing Zheng, Han Meng, Siqi Liang, Anqing Chen, Hiroko H. Dodge, Jiayu Zhou, Zhangyang Wang.

AISTATS 2024 On the Generalization Ability of Unsupervised Pretraining.
Yuyang Deng, Junyuan Hong, Jiayu Zhou, Mehrdad Mahdavi.

ICLR 2024 Safe and Robust Watermark Injection with a Single OoD Image.
Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou.

SaTML 2024 Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk.
Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang.

ICLR (Spotlight) 2024 DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer.
Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang.

NeurIPS-RegML 2023 Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning.
Shuyang Yu, Junyuan Hong, Yi Zeng, Fei Wang, Ruoxi Jia, Jiayu Zhou.

NeurIPS 2023 Understanding Deep Gradient Leakage via Inversion Influence Functions.
Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou.

FL4DM 2023 A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection.
Haobo Zhang, Junyuan Hong, Fan Dong, Steve Drew, Liangjie Xue, Jiayu Zhou.

FL4DM 2023 FedNoisy: A Federated Noisy Label Learning Benchmark.
Siqi Liang, Jintao Huang, Junyuan Hong, Fan Dong, Dun Zeng, Jiayu Zhou, Zenglin Xu.

ICML 2023 Revisiting Data-Free Knowledge Distillation with Poisoned Teachers.
Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou.

TMLR 2023 How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts.
Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang.

ICLR 2023 MECTA: Memory-Economic Continual Test-Time Model Adaptation.
Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger.

ICLR (Spotlight) 2023 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.

AAAI (Oral) 2023 Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning.
Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou.

Preprint 2022 Precautionary Unfairness in Self-Supervised Contrastive Pre-training.
Junyuan Hong, Haotao Wang, Haobo Zhang, Zhangyang Wang, Jiayu Zhou.

NeurIPS 2022 Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling.
Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger.

NeurIPS 2022 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.

ICML 2022 Resilient and Communication Efficient Learning for Heterogeneous Federated Systems.
Zhuangdi Zhu, Junyuan Hong, Steve Drew, Jiayu Zhou.

FAccT 2022 Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent.
Junyuan Hong, Zhangyang Wang, Jiayu Zhou.

ICLR 2022 Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization.
Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou.

KDD 2018 Federated Adversarial Debiasing for Fair and Trasnferable Representations.
Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Hiroko Dodge, Zhangyang Wang, Jiayu Zhou.

ICML 2021 Data-Free Knowledge Distillation for Heterogeneous Federated Learning.
Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou.

AAAI 2021 Learning Model-Based Privacy Protection under Budget Constraints.
Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou.

AD 2020 Detecting MCI using real-time, ecologically valid data capture methodology: How to improve scientific rigor in digital biomarker analyses.
Junyuan Hong, Jeffrey Kaye, Hiroko H Dodge, Jiayu Zhou.

TKDD 2019 Variant Grassmann Manifolds: A Representation Augmentation Method for Action Recognition.
Junyuan Hong, Yang Li, Huanhuan Chen.

TNNLS 2019 Short Sequence Classification Through Discriminable Linear Dynamical System.
Yang Li, Junyuan Hong, Huanhuan Chen.

KDD (Oral) 2018 Disturbance Grassmann Kernels for Subspace-Based Learning.
Junyuan Hong, Huanhuan Chen, Feng Lin.

ECML 2016 Sequential Data Classification in the Space of Liquid State Machines.
Yang Li, Junyuan Hong, Huanhuan Chen.

Featured Publications

A-CONECT: Designing AI-based Conversational Chatbot for Early Dementia Intervention

Junyuan Hong, Wenqing Zheng, Han Meng, Siqi Liang, Anqing Chen, Hiroko H. Dodge, Jiayu Zhou, Zhangyang Wang

We develop a chatbot for early dementia prevention and leverage LLMs to build digital twins to evaluate chatbots.

A-CONECT: Designing AI-based Conversational Chatbot for Early Dementia Intervention

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

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

We make local LLMs to engineer privacy-preserving prompts that are transferrable for cloud models.

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

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

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

We develop a hybrid federated learning for learning financial-crime predictive models from horizontal and vertical federated data structures.

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

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

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

We propose a new privacy-preserving learning framework, outsourcing training to cloud without uploading data, which provides more data without injecting noise into gradient or samples.

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

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

Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

Efficient and federated learning for heterogeneous clients with different memory sizes

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

Federated Adversarial Debiasing for Fair and Trasnferable Representations

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

A distributed domain/group debiasing framework for unsupervised domain adaptation or fairness enhancement.

Federated Adversarial Debiasing for Fair and Trasnferable Representations

Professional Activities

Experience

Postdoctoral Fellow with Dr. Zhangyang Wang, VITA group@UT Austin, IFML and WNCG, 2023-Now.
Research Intern with Dr. Lingjuan Lyu, Sony AI, 2022

Awards

ML and Systems Rising Stars, ML Commons, 2024
Top Reviewer, NeurIPS, 2023
Research Enhancement Award, MSU, 2023
The 3rd place in the U.S. PETs prize challenge, 2023
Dissertation Completion Fellowship, MSU, 2023
Carl V. Page Memorial Graduate Fellowship, MSU, 2021

Fundings

I am grateful that our research is supported by the multiple programs.

OpenAI Researcher Access Program early-dementia prevention via A-CONECT chatbot.
IFML Postdoctoral Fellowship for my research in trustworthy LLMs.

Media Coverage

At Summit for Democracy, the United States and the United Kingdom Announce Winners of Challenge to Drive Innovation in Privacy-enhancing Technologies That Reinforce Democratic Values, The White House, 2023
Privacy-enhancing Research Earns International Attention, MSU Engineering News, 2023
Privacy-Enhancing Research Earns International Attention, MSU Office Of Research And Innovation, 2023

Talks

‘Building Conversational AI for Affordable and Accessible Early Dementia Intervention’ @ AI Health Course, The School of Information, UT Austin, April, 2024: [paper]
‘Shake to Leak: Amplifying the Generative Privacy Risk through Fine-Tuning’ @ Good Systems Symposium: Shaping the Future of Ethical AI, UT Austin, March, 2024: [paper]
‘Foundation Models Meet Data Privacy: Risks and Countermeasures’ @ Trustworthy Machine Learning Course, Virginia Tech, Nov, 2023
‘Economizing Mild-Cognitive-Impairment Research: Developing a Digital Twin Chatbot from Patient Conversations’ @ BABUŠKA FORUM, Nov, 2023: [link]
‘Backdoor Meets Data-Free Learning’ @ Hong Kong Baptist University, Sep, 2023: [slides]
‘MECTA: Memory-Economic Continual Test-Time Model Adaptation’ @ Computer Vision Talks, March, 2023: [slides] [video]
‘Split-Mix Federated Learning for Model Customization’ @ TrustML Young Scientist Seminars, July, 2022: [link] [video]
‘Federated Adversarial Debiasing for Fair and Transferable Representations’, @ CSE Graduate Seminar, Michigan State University, October, 2021: [slides]
‘Dynamic Policies on Differential Private Learning’ @ VITA Seminars, UT Austin, Sep, 2020: [slides]

Teaching

Mentor@Directed Reading Program (DiRP) on Trustworthy LLM, UT Austin, 2023
Teaching Assistant@CSE 847: Machine Learning, MSU, 2021
Teaching Assistant@CSE 404: Introduction to Machine Learning, MSU, 2020

Mentoring

Co-mentored with my advisor:

Zhangheng Li, PhD student at UTAustin, GenAI Privacy (SaTML'24)
Haobo Zhang, PhD student at MSU, DL Privacy (NeurIPS'23)
Shuyang Yu, PhD student at MSU, AI Security (ICLR'24, ICML'23, ICLR'23 Spotlight)

Services

Organizers: GenAI4Health@NeurIPS, The Competition for LLM and Agent Safety 2024, The NeurIPS 2024 LLM Privacy Challenge, FL4Data-Mining Workshop@KDD 2023 (Lead Chair), FedKDD Workshop 2024 (Co-Lead Chair)
External Reviewer: NeurIPS 22-23 (Top Reviewer, 2023), ICML 22-24, ICLR 23-24, KDD 22-24, ECML-PKDD 23, AISTATS 23, WSDM 22, AISTATS 22, AAAI 21-23, IJCAI 19, NeuroComputing, TKDD, TKDE, JAIR, TDSC, ACM Health
Volunteer: KDD 18, 21