Meet ApplyKite Twin, the application assistant that learns with you

Meet your Twin, it learns with you

Your Twin learns with you

Launch week codes:30% off annual Pro20% off monthly Pro

Ends in00h00m00s

Yuan Hong

Associate Professor

University of Connecticut

United States

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Professors in United States Professors in Cybersecurity Cybersecurity professors in United States

About

Yuan Hong is an Associate Professor at the University of Connecticut, USA. His research interests focus on privacy preservation in data streams, federated learning, and user privacy safeguards. Recent publications include works on local differential privacy, data poisoning attacks, and maintaining privacy in various technological contexts, such as large language models and video recognition systems.

Articles (24)

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2026

Year:

2025

Year:

2025

Year:

2025

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Year:

2023

Year:

2023

Year:

2023

Year:

2023

Year:

2023

Year:

2022

Year:

2021

Year:

2021

Year:

2021

Year:

2020

Year:

2020

Collaborators (5)

Shaolin Liao

Professor (Research) & Adjunct Teacher

Illinois Institute of Technology

UNITED STATES

View details

Aichih Chang

Assistant Professor

New Jersey Institute of Technology

UNITED STATES

View details

Yang Cao

Associate Professor

Tokyo Institute of Technology

JAPAN

View details

Shamik Sural

Professor

Indian Institute of Technology, Kharagpur

View details

Xiaochen Li

Assistant Professor

University of North Carolina at Greensboro

UNITED STATES

View details

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Yuan Hong

Research Interests

Make your next move.

Explore related searches

About

Articles (24)

Differentially Private Federated Learning: A Systematic Review

Adversarial Attacks on Locally Private Graph Neural Networks

Concretely Efficient Correlated Oblivious Permutation

SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications

Transferability in data poisoning attacks on spatiotemporal traffic forecasting models

Secure and Efficient Lp-Norm Computation for Two-Party Learning Applications

PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization

Safeguarding Graph Neural Networks against Topology Inference Attacks

Learning Robust and Privacy-Preserving Representations via Information Theory

Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory

FLTracer: Accurate Poisoning Attack Provenance in Federated Learning

PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents

Data poisoning attacks on traffic state estimation and prediction

Stealthy 3D Poisoning Attack on Video Recognition Models

FaceIDP: Face Identification Differential Privacy via Dictionary Learning Neural Networks

Infrastructure-Enabled GPS Spoofing Detection and Correction

UniAP: Protecting Speech Privacy with Non-targeted Universal Adversarial Perturbations

A Generalized Framework for Preserving Both Privacy and Utility in Data Outsourcing

OpBoost: A Vertical Federated Tree Boosting Framework based on Order-Preserving Desensitization

Guest Editors’ Introduction to the Joint Special Section on Secure and Emerging Collaborative Computing and Intelligent Systems

Dynamic Pricing for Electric Vehicle Extreme Fast Charging

VTDP: Privately Sanitizing Fine-grained Vehicle Trajectory Data with Boosted Utility

VideoDP: A Flexible Platform for Video Analytics with Differential Privacy

Releasing Correlated Trajectories: Towards High Utility and Optimal Differential Privacy

Collaborators (5)

Shaolin Liao

Aichih Chang

Yang Cao

Shamik Sural

Xiaochen Li

Make your next move.