Zhicong Huang

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
arxiv, 2026

Changyue Li, Jiaming He, Youliang Yuan, Jialin Wu, Boxi Yu, Zhicong Huang*, Pinjia He*
*Corresponding Author

When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
EMNLP (main), 2026

Zhen Sun, Yifan Liao, Zhicong Huang*, Jiaheng Wei, Cheng Hong, Yutao Yue, Xinlei He*
*Corresponding Author

RBOOT: Accelerating Homomorphic Neural Network Inference by Fusing ReLU within Bootstrapping
Usenix Security, 2026

Zhaomin Yang, Chao Niu, Benqiang Wei, Zhicong Huang, Cheng Hong, Tao Wei

One Bad Token Spoils the Barrel: Assessment, Detection, and Remediation of Glitch Tokens in Large Language Models
Usenix Security, 2026

Kunsheng Tang, Peigui Qi, Yide Song, Wenbo Zhou, Zhicong Huang, Qing Guo, Tianwei Zhang, Weiming Zhang, Nenghai Yu, Jie Zhang

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
ICML, 2026

Changyue Li, Jiaying Li, Youliang Yuan, Jiaming He, Zhicong Huang, Pinjia He

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
ICML, 2026

Jialin Wu, Wei Shi, Han Shen, Peigui Qi, Kunsheng Tang, Zhicong Huang, Binghao Wang, Zhou Yang

Fingerprinting LLMs via Prompt Injection
ACL, 2026

Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Gong

TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
CVPR, 2026

Jiaming He, Guanyu Hou, Hongwei Li, Zhicong Huang*, Kangjie Chen, Yi Yu, Wenbo Jiang, Guowen Xu, Tianwei Zhang
*Corresponding Author

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
To appear in IEEE Symposium on Security & Privacy, 2026

Jialin Wu, Kecen Li, Zhicong Huang*, Xinfeng Li, Xiaofeng Wang, Cheng Hong
*Corresponding Author

Dory: Streaming PCG with Small Memory
To appear in IEEE Symposium on Security & Privacy, 2026
[Github]

Xiaojie Guo, Hanlin Liu, Zhicong Huang, Hongrui Cui, Wenhao Zhang, Cheng Hong, Xiao Wang, Kang Yang, Yu Yu

MARS: A Malignity-Aware Backdoor Defense in Federated Learning
NeurIPS, 2025

Wei Wan, Ning Yuxuan, Zhicong Huang, Cheng Hong, Shengshan Hu, Ziqi Zhou, Yechao Zhang, Tianqing Zhu, Wanlei Zhou, Leo Yu Zhang

PANTHER: Private Approximate Nearest Neighbor Search in the Single Server Setting
CCS, 2025

Jingyu Li, Zhicong Huang, Min Zhang, Jian Liu, Cheng Hong, Tao Wei, Wenguang Chen

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
ICML, 2025
[Github]

Kecen Li, Zhicong Huang*, Xinwen Hou, Cheng Hong
*Corresponding Author

XBOOT: Free-XOR Gates for CKKS with Applications to Transciphering
TCHES, 2025

Chao Niu, Zhicong Huang, Zhaomin Yang, Yi Chen, Liang Kong, Cheng Hong, Tao Wei

SoK: FHE-Friendly Symmetric Ciphers and Transciphering
TCHES, 2025

Chao Niu, Benqiang Wei, Zhicong Huang, Zhaomin Yang, Cheng Hong, Meiqin Wang, Tao Wei

BumbleBee: Secure Two-party Inference Framework for Large Transformers
NDSS, 2025

Wen-jie Lu, Zhicong Huang, Zhen Gu, Jingyu Li, Jian Liu, Cheng Hong, Kui Ren, Tao Wei, WenGuang Chen

Coral: Maliciously Secure Computation Framework for Packed and Mixed Circuits
CCS, 2024
[Github]

Zhicong Huang, Wen-jie Lu, Yuchen Wang, Cheng Hong, Tao Wei, WenGuang Chen

Sublinear Distributed Product Checks on Replicated Secret-Shared Data over Z2k Without Ring Extensions
CCS, 2024

Yun Li, Daniel Escudero, Yufei Duan, Zhicong Huang, Cheng Hong, Chao Zhang, Yifan Song

Accelerating Secure Collaborative Machine Learning with Protocol-Aware RDMA
Usenix Security, 2024

Zhenghang Ren, Mingxuan Fan, Zilong Wang, Junxue Zhang, Chaoliang Zeng, Zhicong Huang, Cheng Hong, and Kai Chen

Efficient 3PC for Binary Circuits with Application to Maliciously-Secure DNN Inference
Usenix Security, 2023

Yun Li, Yufei Duan, Zhicong Huang, Cheng Hong, Chao Zhang, Yifan Song

Squirrel: A Scalable Secure Two-Party Computation Framework for Training Gradient Boosting Decision Tree
Usenix Security, 2023

Wen-jie Lu, Zhicong Huang, Qizhi Zhang, Yuchen Wang, Cheng Hong

Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference
Usenix Security, 2022
[Github]

Zhicong Huang, Wen-jie Lu, Cheng Hong, Jiansheng Ding

More Efficient Secure Matrix Multiplication for Unbalanced Recommender Systems
IEEE Transactions on Dependable and Secure Computing (TDSC), 2021
[Github]

Zhicong Huang, Cheng Hong, Wen-jie Lu, Chenkai Weng, Hunter Qu

PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption
42th IEEE Symposium on Security and Privacy, 2021

Wen-jie Lu, Zhicong Huang, Cheng Hong, Yiping Ma, Hunter Qu

Improving Utility and Security of the Shuffler-based Differential Privacy
VLDB 2021

Tianhao Wang, Bolin Ding, Min Xu, Zhicong Huang, Cheng Hong, Jingren Zhou, Ninghui Li, Somesh Jha

Answering Multi-Dimensional Analytical Queries under Local Differential Privacy
SIGMOD, 2019

Tianhao Wang, Bolin Ding, Jingren Zhou, Cheng Hong, Zhicong Huang, Ninghui Li, Somesh Jha

Quantification of the Leakage in Federated Learning
FL-NeurIPS (Workshop), 2019

Zhaorui Li, Zhicong Huang, Chaochao Chen, Cheng Hong

DPSAaS: Multi-Dimensional Data Sharing and Analytics as Services under Local Differential Privacy
VLDB Demonstration, 2019

Min Xu, Tianhao Wang, Bolin Ding, Jingren Zhou, Cheng Hong, and Zhicong Huang

Labeled PSI from Fully Homomorphic Encryption with Malicious Security
25th ACM SIGSAC Conference on Computer and Communications Security, 2018

Hao Chen, Zhicong Huang, Kim Laine, Peter Rindal

Logistic regression over encrypted data from fully homomorphic encryption
2018

Hao Chen, Ran Gilad-Bachrach, Kyoohyung Han, Zhicong Huang, Amir Jalali, Kim Laine, Kristin Lauter

SQC: Secure Quality Control for Meta-Analysis of Genome-Wide Association Studies
Bioinformatics, 2017

Zhicong Huang, Huang Lin, Jacques Fellay, Zoltan Kutalik, Jean-Pierre Hubaux

UnLynx: A Decentralized System for Privacy-Conscious Data Sharing
Proceedings on Privacy Enhancing Technologies, 2017

David Froelicher, Patricia Egger, João Sá Sousa, Jean Louis Raisaro, Zhicong Huang, Christian Mouchet, Bryan Ford, and Jean-Pierre Hubaux

Efficient and Secure Outsourcing of Genomic Data Storage
BMC medical genomics, 2017

João Sá Sousa, Cédric Lefebvre, Zhicong Huang, Jean Louis Raisaro, Carlos Aguilar, Marc-Olivier Killijian, Jean-Pierre Hubaux

A privacy-preserving solution for compressed storage and selective retrieval of genomic data
Genome Research, 2016

Zhicong Huang, Erman Ayday, Huang Lin, Raeka S Aiyar, Adam Molyneaux, Zhenyu Xu, Jacques Fellay, Lars M Steinmetz, Jean-Pierre Hubaux

GenoGuard: Protecting genomic data against brute-force attacks
36th IEEE Symposium on Security and Privacy, 2015

Zhicong Huang, Erman Ayday, Jacques Fellay, Jean-Pierre Hubaux, Ari Juels
Distinguished Paper Award

Differential privacy with bounded priors: reconciling utility and privacy in genome-wide association studies
22nd ACM SIGSAC Conference on Computer and Communications Security, 2015

Florian Tramèr, Zhicong Huang, Jean-Pierre Hubaux, Erman Ayday

Quantifying genomic privacy via inference attack with high-order SNV correlations
International Workshop on Genome Privacy and Security (in conjunction with IEEE S&P), 2015

Sahel S. Samani, Zhicong Huang, Erman Ayday, Mark Elliot, Jacques Fellay, Jean-Pierre Hubaux, Zoltan Kutalik

CredibleWeb: A Platform for Web Credibility Evaluation
CHI'13 Extended Abstracts on Human Factors in Computing Systems, 2013

Zhicong Huang, Alexandra Olteanu, Karl Aberer

Researcher

Programmer

Traveler

Movie enthusiast

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment arxiv, 2026

When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer EMNLP (main), 2026

RBOOT: Accelerating Homomorphic Neural Network Inference by Fusing ReLU within Bootstrapping Usenix Security, 2026

One Bad Token Spoils the Barrel: Assessment, Detection, and Remediation of Glitch Tokens in Large Language Models Usenix Security, 2026

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation ICML, 2026

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models ICML, 2026

Fingerprinting LLMs via Prompt Injection ACL, 2026

TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models CVPR, 2026

EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models To appear in IEEE Symposium on Security & Privacy, 2026

Dory: Streaming PCG with Small Memory To appear in IEEE Symposium on Security & Privacy, 2026 [Github]

MARS: A Malignity-Aware Backdoor Defense in Federated Learning NeurIPS, 2025

PANTHER: Private Approximate Nearest Neighbor Search in the Single Server Setting CCS, 2025

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models ICML, 2025 [Github]

XBOOT: Free-XOR Gates for CKKS with Applications to Transciphering TCHES, 2025

SoK: FHE-Friendly Symmetric Ciphers and Transciphering TCHES, 2025

BumbleBee: Secure Two-party Inference Framework for Large Transformers NDSS, 2025

Coral: Maliciously Secure Computation Framework for Packed and Mixed Circuits CCS, 2024 [Github]

Sublinear Distributed Product Checks on Replicated Secret-Shared Data over Z2k Without Ring Extensions CCS, 2024

Accelerating Secure Collaborative Machine Learning with Protocol-Aware RDMA Usenix Security, 2024

Efficient 3PC for Binary Circuits with Application to Maliciously-Secure DNN Inference Usenix Security, 2023

Squirrel: A Scalable Secure Two-Party Computation Framework for Training Gradient Boosting Decision Tree Usenix Security, 2023

Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference Usenix Security, 2022 [Github]

More Efficient Secure Matrix Multiplication for Unbalanced Recommender Systems IEEE Transactions on Dependable and Secure Computing (TDSC), 2021 [Github]

PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption 42th IEEE Symposium on Security and Privacy, 2021

Improving Utility and Security of the Shuffler-based Differential Privacy VLDB 2021

Answering Multi-Dimensional Analytical Queries under Local Differential Privacy SIGMOD, 2019

Quantification of the Leakage in Federated Learning FL-NeurIPS (Workshop), 2019

DPSAaS: Multi-Dimensional Data Sharing and Analytics as Services under Local Differential Privacy VLDB Demonstration, 2019

Labeled PSI from Fully Homomorphic Encryption with Malicious Security 25th ACM SIGSAC Conference on Computer and Communications Security, 2018

Logistic regression over encrypted data from fully homomorphic encryption 2018

SQC: Secure Quality Control for Meta-Analysis of Genome-Wide Association Studies Bioinformatics, 2017

UnLynx: A Decentralized System for Privacy-Conscious Data Sharing Proceedings on Privacy Enhancing Technologies, 2017

Efficient and Secure Outsourcing of Genomic Data Storage BMC medical genomics, 2017

A privacy-preserving solution for compressed storage and selective retrieval of genomic data Genome Research, 2016

GenoGuard: Protecting genomic data against brute-force attacks 36th IEEE Symposium on Security and Privacy, 2015

Differential privacy with bounded priors: reconciling utility and privacy in genome-wide association studies 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015

Quantifying genomic privacy via inference attack with high-order SNV correlations International Workshop on Genome Privacy and Security (in conjunction with IEEE S&P), 2015

CredibleWeb: A Platform for Web Credibility Evaluation CHI'13 Extended Abstracts on Human Factors in Computing Systems, 2013

Java

C/C++

Python

Web Dev

Numpy

Tensorflow

Ph.D. Degree, Computer Science, EPFL (2012-2018)

Bachelor Degree, Computer Science, Peking University (2008-2012)

Research scientist, Ant Group 2023--

Staff Security Engineer, Alibaba Group 2022--2023

Senior Security Engineer, Alibaba Group 2018--2022

Research Intern, Microsoft Research (Redmond) 2017