Peichun Hua | CUHK-Shenzhen

About Me

I completed my bachelor’s in Computer Science at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen). I was an exchange tar heel at the University of North Carolina at Chapel Hill in Year 2024-25.

My research interests span adversarial machine learning, information retrieval, privacy computing, and hardware security. Recently I am interested in threats and defense problems in agentic AI, information retrieval, and emerging paradigms of RAG. I am always open to research discussions and collaborations!

I am fortunate to work with Prof. Yue Zheng and Prof. Yunming Xiao during my undergraduate study at CUHK-Shenzhen. In the summer of 2025, I was an international student research intern at Washington University in St. Louis, advised by Prof. Ning Zhang. I also work closely with Prof. Mengyuan Li in Summer 2026.

I am currently looking for PhD positions starting in Fall 2027. Please let me know if you happen to be recruiting or know someone that is!

Publications

Preprints

Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs

Junguang Yao, Peichun Hua, Hanxiu Zhang, and Yue Zheng

arXiv preprint, 2026. arXiv

PDF Link Bib

@article{yao2026label, title={Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs}, author={Junguang Yao and Peichun Hua and Hanxiu Zhang and Yue Zheng}, journal={CoRR}, volume={abs/2610.32079}, year={2026}, url={https://arxiv.org/abs/2610.32079}, doi={10.48550/arXiv.2610.32079}, eprinttype={arXiv}, eprint={2610.32079}, primaryClass={cs.CR} }
Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG

Suting Chen^*, Peichun Hua^*, and Yunming Xiao

arXiv preprint, 2026. arXiv

PDF Link Bib

^* Equal contribution.

@article{chen2026relevance, title={Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG}, author={Suting Chen and Peichun Hua and Yunming Xiao}, journal={CoRR}, volume={abs/2609.37469}, year={2026}, url={https://arxiv.org/abs/2609.37469}, doi={10.48550/arXiv.2609.37469}, eprinttype={arXiv}, eprint={2609.37469}, primaryClass={cs.CL} }
Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers

Beining Xu^*, Peichun Hua^*, and Yunming Xiao

arXiv preprint, 2026. arXiv

PDF Link Bib

^* Equal contribution.

@article{xu2026backdoor, title={Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers}, author={Beining Xu and Peichun Hua and Yunming Xiao}, journal={CoRR}, volume={abs/2609.37468}, year={2026}, url={https://arxiv.org/abs/2609.37468}, doi={10.48550/arXiv.2609.37468}, eprinttype={arXiv}, eprint={2609.37468}, primaryClass={cs.CR} }
Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval

Peichun Hua and Yunming Xiao

arXiv preprint 2026 arXiv

PDF Link Bib

@article{hua2026matryoshka, title={Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval}, author={Peichun Hua and Yunming Xiao}, journal={CoRR}, volume={abs/2609.07276}, year={2026}, url={https://arxiv.org/abs/2609.07276}, doi={10.48550/arXiv.2609.07276}, eprinttype={arXiv}, eprint={2609.07276}, primaryClass={cs.IR} }
Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings

Peichun Hua and Yunming Xiao

arXiv preprint 2026 arXiv

PDF Link Bib

@article{hua2026spruce, title={Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings}, author={Peichun Hua and Yunming Xiao}, journal={CoRR}, volume={abs/2609.03376}, year={2026}, url={https://arxiv.org/abs/2609.03376}, doi={10.48550/arXiv.2609.03376}, eprinttype={arXiv}, eprint={2609.03376}, primaryClass={cs.CR} }
Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, and Yunming Xiao

arXiv preprint 2026 arXiv

PDF Link Bib

@article{hua2026pointing, author = {Peichun Hua and Danyang Chen and Junan Zhang and Haifeng Sun and Jingyu Wang and Diwen Xue and Mingyu Li and Yunming Xiao}, title = {Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale}, journal = {CoRR}, volume = {abs/2608.25735}, year = {2026}, url = {https://arxiv.org/abs/2608.25735}, doi = {10.48550/arXiv.2608.25735}, eprinttype = {arXiv}, eprint = {2608.25735} }
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills

Peichun Hua, Haoxuan Xu, and Mengyuan Li

arXiv preprint 2026 arXiv

PDF Link Bib

@article{hua2026skillclone, title={Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills}, author={Peichun Hua and Haoxuan Xu and Mengyuan Li}, journal={CoRR}, volume={abs/2608.04192}, year={2026}, url={https://arxiv.org/abs/2608.04192}, doi={10.48550/arXiv.2608.04192}, eprinttype={arXiv}, eprint={2608.04192}, primaryClass={cs.CR} }

Accepted / Published

Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents

Peichun Hua and Yunming Xiao

ACM Workshop on Hot Topics in Networks (HotNets), 2026. HotNets

PDF Link Code Bib

Accepted. Acceptance Rate: 43/188 ≈ 22.9%.

@inproceedings{hua2026semantics, title={Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents}, author={Peichun Hua and Yunming Xiao}, booktitle={The 25th ACM Workshop on Hot Topics in Networks (HotNets '26)}, year={2026}, publisher={Association for Computing Machinery}, address={New York, NY, USA}, url={https://doi.org/10.1145/3847290.3859940}, doi={10.1145/3847290.3859940}, numpages={13}, keywords={Content Delivery Networks, Retrieval-Augmented Generation, Agentic Search, Semantic Caching, Vector Search}, location={Salt Lake City, UT, USA}, series={HotNets '26} }
Enroll Once, Identify Everywhere: Few-Shot Cross-Scenario Visual Speaker Recognition via Event-driven SlowFast Networks

Junguang Yao, Peichun Hua, and Yue Zheng

The 23rd Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2026. PRICAI

PDF Code Bib

Acceptance Rate: 542/1825 ≈ 29.7%. Accepted as a Regular Paper, Oral Presentation.

@inproceedings{yao2026enroll, title={Enroll Once, Identify Everywhere: Few-Shot Cross-Scenario Visual Speaker Recognition via Event-driven SlowFast Networks}, author={Junguang Yao and Peichun Hua and Yue Zheng}, booktitle={The 23rd Pacific Rim International Conference on Artificial Intelligence (PRICAI)}, year={2026}, organization={Springer} }
Unlocking Software-defined GPU Fabric Scheduling in the LLM Era

Danyang Chen, Yufeng Gu, Yibo Huang, Chengxuan Pei, Peichun Hua, Yang Zhou, and Yunming Xiao

ACM SIGOPS Asia-Pacific Workshop on Systems (APSys), 2026. APSys

PDF Link Code Slides Bib

Accepted. Acceptance Rate: 19/43 ≈ 44%.

@inproceedings{chen2026gpuweaver, title={Unlocking Software-defined GPU Fabric Scheduling in the LLM Era}, author={Danyang Chen and Yufeng Gu and Yibo Huang and Chengxuan Pei and Peichun Hua and Yang Zhou and Yunming Xiao}, booktitle={ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)}, year={2026}, isbn = {9798400729126}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3838177.3841731}, numpages = {8}, keywords = {GPU fabrics, datacenter systems, heterogeneous accelerators, machine learning systems, communication scheduling, resource contention, PCIe, NVLink, RDMA, LLM serving}, location = {Bangkok Marriott Marquis Queen's Park, Bangkok, Thailand}, series = {APSys '26} pages={118--125}, doi={10.1145/3838177.3841731}, }
A Unified Open-Set Framework for Scalable PUF-Based Authentication of Heterogeneous IoT Devices

Xin Wang, Peichun Hua, Chip Hong Chang, Wenye Liu, and Yue Zheng

IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2026. SMC

PDF Link Code Bib

Accepted.

@inproceedings{wang2026openpuf, title={A Unified Open-Set Framework for Scalable PUF-Based Authentication of Heterogeneous IoT Devices}, author={Xin Wang and Peichun Hua and Chip Hong Chang and Wenye Liu and Yue Zheng}, booktitle={IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, year={2026}, organization={IEEE} }
Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring

Peichun Hua, Hao Li, Shanghao Shi, Zhiyuan Yu, and Ning Zhang

The 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026. ACL

PDF Link Code Slides Video Bib

Accepted as Oral Presentation of Main Conference (Top 20% of Accepted Papers). Acceptance Rate: around 2300/12148 ≈ 19%.

@inproceedings{hua2026rethinking, title = "Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring", author = {Hua, Peichun and Li, Hao and Shi, Shanghao and Yu, Zhiyuan and Zhang, Ning}, editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David}, booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.acl-long.992/", pages = "21748--21785", ISBN = "979-8-89176-390-6", }
Live Demonstration: Hardware-Bound IP Protection for OWL-ViT on Edge Devices

Peichun Hua, Hanxiu Zhang, Tuo Li, Yue Zheng, and Wenye Liu

IEEE International Symposium on Circuits and Systems (ISCAS), 2026. ISCAS

PDF Link Code Bib

Accepted for Live Presentation.

@inproceedings{hua2026live, title={Live Demonstration: Hardware-Bound IP Protection for OWL-ViT on Edge Devices}, author={Hua, Peichun and Zhang, Hanxiu and Li, Tuo and Zheng, Yue and Liu, Wenye}, booktitle={IEEE International Symposium on Circuits and Systems (ISCAS)}, year={2026}, pages={10-10}, doi={10.1109/ISCAS66217.2026.11562768}, organization={IEEE} }
Securing On-device Transformer with Hardware Binding and Reversible Obfuscation

Peichun Hua, Hanxiu Zhang, Tuo Li, and Yue Zheng

The 41st Annual Computer Security Applications Conference (ACSAC), 2025. ACSAC

PDF Link Code Slides Video Bib

Acceptance Rate: 84/446 ≈ 18.8%. Artifact Available, Artifact Reviewed, Artifact Reproducible (IEEE Badges, 34/84 among accepted papers).

@inproceedings{hua2025securing, title={Securing On-device Transformer with Hardware Binding and Reversible Obfuscation}, author={Hua, Peichun and Zhang, Hanxiu and Li, Tuo and Zheng, Yue}, pages={956-972}, booktitle={2025 IEEE Annual Computer Security Applications Conference (ACSAC)}, year={2025}, organization={IEEE}, keywords={Deep learning;Computational modeling;Intellectual property;Transformers;Physical unclonable function;Hardware;Software;Data models;Protection;Software development management;Intellectual Property;Transformer;Model Stealing Attacks;Physical Unclonable Functions}, doi={10.1109/ACSAC67867.2025.00079}, }

Services

2026

Awards

Academic Honors

Outstanding Graduate, School of Data Science, CUHK-Shenzhen — 2026
Dean's List, School of Data Science, CUHK-Shenzhen — 2022–2023, 2023–2024, 2025–2026
Academic Performance Scholarship (Class B, Top <2%), School of Data Science — 2023–2024
Academic Performance Scholarship (Class C, Top <5%), School of Data Science — 2022–2023
University Research Award (with scholarship) — 2024 Fall, 2025 Spring

Research Awards

Student Travel Grant, 25th ACM Workshop on Hot Topics in Networks (HotNets 2026) — 2026
Student Conferenceship, 41st Annual Computer Security Applications Conference (ACSAC 2025) — Dec. 2025
Artifact Available, Artifact Reviewed, and Artifact Reproducible Badges — IEEE — for paper 'Securing On-device Transformer with Hardware Binding and Reversible Obfuscation' at ACSAC 2025
Fully Funded International Research Internship — McKelvey School of Engineering, Washington University in St. Louis — Summer 2025