Welcome to Yuan Hong's Homepage

Address: 371 Fairfield Way
Unit 4155, Storrs, CT 06269

Office: ITE-265
Email: yuan.hong AT uconn.edu

Short Bio

Dr. Yuan Hong is a Collins Aerospace Endowed Associate Professor in the School of Computing at University of Connecticut (UConn) and affiliated with the Connecticut Advanced Computing Center (CACC). Prior to joining UConn, he was an Assistant Professor in Computer Science and Cybersecurity Program Director at Illinois Institute of Technology between 2017 and 2022. He received his Ph.D degree from Rutgers University, M.Sc degree from Concordia University, Montreal, Canada, and B.Sc degree from Beijing Institute of Technology, respectively. He is a recipient of the NSF CAREER Award (2021), CCS Distinguished Paper Award (2024), CCS Top Reviewer Award (2025), USENIX Security Notable Reviewer Award (2025), and multiple Cisco Research Awards, and was also recognized as the finalist of the Meta Research Award (2021). He also received a National Physics Olympiad Prize in China. His research spans Security, Privacy, and Trustworthy Machine Learning, with a focus on differential privacy, secure computation, applied cryptography, adversarially robust learning in the context of computer vision, (large) language models, and cyber-physical systems (CPS). His research has been published in top conferences across Security, Databases, Machine Learning, Computer Vision, and NLP, such as S&P, CCS, USENIX Security, NDSS, CSF, PETS, SIGMOD, VLDB, NeurIPS, ICLR, CVPR, ECCV, EMNLP, KDD, and AAAI, as well as top journals (e.g., ACM Computing Surveys, multiple IEEE/ACM Transactions, and Transportation Research). He is a Senior Member of the ACM and IEEE.

We have Ph.D. openings available. If you are interested in our research, please email your application materials to Dr. Yuan Hong.

UConn@CSRankings: Security & Crypto (30th), Overall (63rd)

News

[Recent Conference Organization] Web'27 (Track Chair), AsiaCCS'27 (Track Chair), S&P'27 (Workshop Review Committee)
[Recent Conference TPC] S&P'27, NDSS'27, NeurIPS'26 (Area Chair), CCS'26, USENIX Security'26, S&P'26, NDSS'26
[09/2026] Our SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses is accepted to S&P'27 (Acceptance Rate: 160/1012=15.8%). Congrats to Hanbin, Shuang (co-first authors) and the team! Dataset (including 1,000,000+ annotated jailbreaking and benign prompts), Code and Leaderboard are online.
[08/2026] Our CodeScan on detecting data poisoning in code-generation LLMs is accepted to CCS'26 (Acceptance Rate: TBD). Congrats to Shenao and the team!
[08/2026] Yuan will serve as the Track Chair in Security and Privacy at ACM Web Conference 2027.
[08/2026] Nima and Jie received the USENIX Security'26 Noteworthy Reviewer Award for Artifact Evaluations, Congrats!
[07/2026] Our USENIX Security'26 paper got three (Available, Functional/Reusable, Results Reproduced) badges for the artifacts Congrats!
[07/2026] Our work on Crypto L^p-Norm is accepted to TIFS. Congrats to Ali, Joshua, Bingyu and the team!
[06/2026] Our work on human-perceptible adversarial attacks on LLM-powered content moderation systems is accepted to USENIX Security'26 (Acceptance Rate: 362/3028=12.0%). Congrats to Qin, Lu and the team!
[05/2026] Welcome Jie to our lab as a visiting Ph.D. student in Summer 2026. Shenao will join Google DeepMind as a research intern in Summer 2026. Congrats!
[03/2026] Our work on concretely efficient correlated oblivious permutation is accepted to ASIACCS'26 (Acceptance Rate: 47/276=17.0%). Congrats!
[03/2026] Our work on revisiting privacy leakage in machine unlearning is accepted to EuroS&P'26 (Acceptance Rate: 50/460=11.7%). Congrats to Jie and Nima!
[01/2026] Yuan will serve as the Track Chair in Privacy and Anonymity at ACM ASIACCS'27.
[01/2026] Our work on CogniMap3D is accepted to ICLR'26 (Acceptance Rate: 28%). Congrats!
[01/2026] Our work on theoretically understanding data reconstruction leakage in federated learning is accepted to TMLR. Congrats!
[01/2026] Welcome Shuang Wu and Luis Mendez to join our DataSec Lab!
[12/2025] Our transferable attacks on spatiotemporal traffic forecasting models is accepted to Transportation Research Part C (IF: 7.9). Congrats!
[12/2025] Our new taxonomy and review for differentially private federated learning is accepted to ACM Computing Surveys (IF: 28.0). Congrats to Jie and the team!
[11/2025] Our work on SecureV2X is accepted to ACM SAC'26 (Acceptance Rate: 225/961=23.4%). Congrats to Joshua and Ali!
[10/2025] Our Laplace DP-SGD for high dimensions via majorization theory is accepted to CSF'26 after shepherding (a prestigious venue for computer security foundation). Congrats to Meisam, Qin and the team!
[10/2025] Yuan received the CCS'25 Top Reviewer Award and Nima received the CCS'25 Distinguished Artifact Evaluation Award, Thanks and Congrats!
[10/2025] Our two CCS'25 papers got three (Available, Functional/Reusable, Results Reproduced) badges for the artifacts Congrats!
[09/2025] Our work on certified robustness with universal asymmetric randomization is accepted to CSF'26 (a prestigious venue for computer security foundation). Congrats to Hanbin!
[09/2025] Thrilled to lead an NSF/FHWA PDaSP multi-disciplinary project (across four institutions) on building a holistic system for privately sharing naturalistic driving data (very grateful to NSF/FHWA for the generous support!)
[08/2025] Our patent on differentially private outsourcing system on anomaly detection is official (US Patent US12399985B2). Congrats to Meisam, Han and the team!
[08/2025] Our work on differentially private embedding distillation is accepted to EMNLP'25 (Main Conference, Acceptance Rate: 22.16%). Congrats to Shuya!
[08/2025] Yuan is recognized as the Notable Reviewer by USENIX Security'25, Thanks!
[08/2025] Hanbin has successfully defended his doctoral dissertation. He will join TikTok as a Research Scientist, Congrats!
[07/2025] Congrats to Nima for receiving the USENIX Security'25 Student Travel Award. Thanks for the generous support!
[07/2025] Our work on optimizing DP for deep learning (including ViT and Language Model Fine-tuning) is accepted to CCS'25 (Acceptance Rate: 316/2,278=13.87%). Congrats to Qin, Nicholas, Meisam and the team!
[07/2025] Our work on safeguarding graph neural networks against topology inference attacks is accepted to CCS'25 (Acceptance Rate: 316/2,278=13.87%). Congrats to Jie and the team!
[06/2025] Our patent on utility-optimized differential privacy system is official (US Patent US12321478B2). Congrats to Meisam, Shangyu and the team!
[06/2025] Shuya has successfully defended her doctoral dissertation. She will join University of Alabama at Birmingham as a Tenure-Track Assistant Professor, Congrats!
[06/2025] Our work on rectifying machine unlearning measurements is accepted to USENIX Security'25 (Acceptance Rate: 407/2385=17.1%). Congrats to Nima, Shenao and the team!
[05/2025] Thrilled to lead an NSF CSR project on building secure and real-time multi-camera surveillance systems (very grateful to NSF for the generous support!)
[05/2025] Congrats to Shuya for receiving the Taylor L. Booth Graduate Fellowship (SoC's highest honor for Ph.D. students). Also, congrats to other students who received the Predoctoral Fellowships!

Selected Recent Publications

S&P'27: SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses [Code, Dataset (including 1,000,000+ Annotated Jailbreaking and Benign Prompts), Leaderboard]
Crypto ePrint: KPIR-C: Keyword PIR with Arbitrary Server-side Computation [Code Available Soon]
CCS'26: Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning [Code Available Soon]
USENIX Security'26: What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks [Code]
ICLR'26: CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval [Code]
CSF'26: Lap₂: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory [Code]
CSF'26: Towards Strong Certified Defense with Universal Asymmetric Randomization [Code]
EMNLP'25: DPED: Multi-Layer Noise Distillation for Privacy-Preserving Text Embeddings [Code]
CCS'25: PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization [Code]
CCS'25: Safeguarding Graph Neural Networks against Topology Inference Attacks [Code]
USENIX Security'25: Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective [Code]
AAAI'25: Learning Robust and Privacy-Preserving Representations via Information Theory [Code]
NDSS'25: Delay-Allowed Differentially Private Data Stream Release [Code]
NeurIPS'24: FedGMark: Certifiably Robust Watermarking for Federated Graph Learning [Code]
CCS'24: Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence [Code]
CCS'24: Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses [Code]
USENIX Security'24: An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection [Code, Dataset]
USENIX Security'24: Inf²Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks [Code]
CVPR'24: On the Faithfulness of Vision Transformer Explanations [Code]
SIGMOD'24: Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory [Code]
S&P'24: DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming [Code]
S&P'24: Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks [Code]
AAAI'24: Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning Against Attribute Inference Attacks [Code]
VLDB'23: OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization [Code]
CCS'22: L-SRR: Local Differential Privacy for Location-Based Services with Staircase Randomized Response [Code]
KDD'22: A Model-Agnostic Approach to Differentially Private Topic Mining [Code]
ECCV'22: UniCR: Universally Approximated Certified Robustness via Randomized Smoothing [Code]
S&P'22: Universal 3-Dimensional Perturbations for Blackbox Attacks on Video Recognition Systems [Code]

Teaching

Principles of Databases: Fall 25, Fall 26
Cybersecurity Lab: Fall 23, Spring 24, Fall 24
Computer Security: Spring 23, Spring 25, Spring 26
CSE Design Project: 2022-2023, 2025-2026, 2026-2027
Cryptography: Spring 21, Spring 20
Data Privacy and Security: Fall 21, Fall 20, Spring 19, Spring 18
Database Organization: Spring 22, Fall 19, Fall 18, Fall 17
Doctoral Seminar: Spring 18
Earlier Teaching: Cybercrime, Forensics, Computer Network