LoopLeap Lab AI for science and health

Research

LoopLeap Lab advances foundational AI through interdisciplinary science and engineering. We build secure, efficient, and reliable AI systems to support scientific discovery and improve health.

We connect AI foundations, systems, and domain expertise to turn new ideas into useful tools. Our research addresses privacy, security, scalability, and efficiency so AI can work across disciplines and real-world settings.

Highlighted

DAHE: Parameter-Adaptive and Memory Efficient FPGA Acceleration of Homomorphic Encryption
DAHE: Parameter-Adaptive and Memory Efficient FPGA Acceleration of Homomorphic Encryption
Yilan Zhu, Honghui You, Wei Zhang, Jiming Xu, Qian Lou, Shoumeng Yan, Lei Ju
IEEE Transactions on Computers  ·  01 Aug 2025  ·  doi:10.1109/TC.2025.3569159

All

2025

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou
arXiv  ·  23 Sep 2025  ·  arXiv:2509.07755
DAHE: Parameter-Adaptive and Memory Efficient FPGA Acceleration of Homomorphic Encryption
DAHE: Parameter-Adaptive and Memory Efficient FPGA Acceleration of Homomorphic Encryption
Yilan Zhu, Honghui You, Wei Zhang, Jiming Xu, Qian Lou, Shoumeng Yan, Lei Ju
IEEE Transactions on Computers  ·  01 Aug 2025  ·  doi:10.1109/TC.2025.3569159
Corrosion Hammer: A Self-Activated Bit-Flip Attack to the Processing-In-Memory Accelerator
Corrosion Hammer: A Self-Activated Bit-Flip Attack to the Processing-In-Memory Accelerator
Zihao Yang, Mengxin Zheng, Shengyu Fan, Qian Lou, Rui Hou, Dan Meng, Mingzhe Zhang
Proceedings of the 22nd ACM International Conference on Computing Frontiers  ·  28 May 2025  ·  doi:10.1145/3719276.3725191
DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data
DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data
Muhammad Husni Santriaji, Jiaqi Xue, Yancheng Zhang, Qian Lou, Yan Solihin
2025 IEEE Symposium on Security and Privacy (SP)  ·  12 May 2025  ·  doi:10.1109/SP61157.2025.00078
zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing
zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing
Yancheng Zhang, Mengxin Zheng, Xun Chen, Jingtong Hu, Weidong Shi, Lei Ju, Yan Solihin, Qian Lou
arXiv  ·  17 Apr 2025  ·  arxiv:2504.12217

2024

WBP: Training-Time Backdoor Attacks Through Hardware-Based Weight Bit Poisoning
WBP: Training-Time Backdoor Attacks Through Hardware-Based Weight Bit Poisoning
Kunbei Cai, Zhenkai Zhang, Qian Lou, Fan Yao
Lecture Notes in Computer Science  ·  21 Nov 2024  ·  doi:10.1007/978-3-031-73650-6_11
Trinity: A General Purpose FHE Accelerator
Trinity: A General Purpose FHE Accelerator
Xianglong Deng, Shengyu Fan, Zhicheng Hu, Zhuoyu Tian, Zihao Yang, …, Dan Meng, Rui Hou, Meng Li, Qian Lou, Mingzhe Zhang
arXiv  ·  18 Oct 2024  ·  arxiv:2410.13405
BoostCom: Towards Efficient Universal Fully Homomorphic Encryption by Boosting the Word-wise Comparisons
BoostCom: Towards Efficient Universal Fully Homomorphic Encryption by Boosting the Word-wise Comparisons
Ardhi Wiratama Baskara Yudha, Jiaqi Xue, Qian Lou, Huiyang Zhou, Yan Solihin
Proceedings of the 2024 International Conference on Parallel Architectures and Compilation Techniques  ·  13 Oct 2024  ·  doi:10.1145/3656019.3676893
OFHE: An Electro-Optical Accelerator for Discretized TFHE
OFHE: An Electro-Optical Accelerator for Discretized TFHE
Mengxin Zheng, Cheng Chu, Qian Lou, Nathan Youngblood, Mo Li, Sajjad Moazeni, Lei Jiang
Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design  ·  05 Aug 2024  ·  doi:10.1145/3665314.3670839
Ar-Spider: Text-to-SQL in Arabic
Ar-Spider: Text-to-SQL in Arabic
Saleh Almohaimeed, Saad Almohaimeed, Mansour Al Ghanim, Liqiang Wang
Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing  ·  08 Apr 2024  ·  doi:10.1145/3605098.3636065
Jailbreaking LLMs with Arabic Transliteration and Arabizi
Jailbreaking LLMs with Arabic Transliteration and Arabizi
Mansour Al Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, Qian Lou
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing  ·  01 Jan 2024  ·  doi:10.18653/v1/2024.emnlp-main.1034
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
Jiaqi Xue, Qian Lou, Mengxin Zheng
Findings of the Association for Computational Linguistics: EMNLP 2024  ·  01 Jan 2024  ·  doi:10.18653/v1/2024.findings-emnlp.484

2023

TrojFair: Trojan Fairness Attacks
TrojFair: Trojan Fairness Attacks
Jiaqi Xue, Mengxin Zheng, Yi Sheng, Lei Yang, Qian Lou, Lei Jiang
Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis  ·  19 Nov 2023  ·  doi:10.1145/3689217.3690620
HEBridge: Connecting Arithmetic and Logic Operations in FV-style HE Schemes
HEBridge: Connecting Arithmetic and Logic Operations in FV-style HE Schemes
Yancheng Zhang, Xun Chen, Qian Lou
Proceedings of the 12th Workshop on Encrypted Computing & Applied Homomorphic Cryptography  ·  19 Nov 2023  ·  doi:10.1145/3689945.3694807
CryptoTrain: Fast Secure Training on Encrypted Dataset
CryptoTrain: Fast Secure Training on Encrypted Dataset
Jiaqi Xue, Yancheng Zhang, Yanshan Wang, Xueqiang Wang, Hao Zheng, Qian Lou
Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis  ·  19 Nov 2023  ·  doi:10.1145/3689217.3690617
TrojBits: A Hardware Aware Inference-Time Attack on Transformer-Based Language Models
TrojBits: A Hardware Aware Inference-Time Attack on Transformer-Based Language Models
Mansour Al Ghanim, Muhammad Santriaji, Qian Lou, Yan Solihin
Frontiers in Artificial Intelligence and Applications  ·  28 Sep 2023  ·  doi:10.3233/faia230254
She: A fast and accurate deep neural network for encrypted data
She: A fast and accurate deep neural network for encrypted data
Advances in Neural Information Processing Systems  ·  14 Jan 2023  ·  [no id info]

2022

CryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
CryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
Mengxin Zheng, Qian Lou, Fan Chen, Lei Jiang, Yongxin Zhu
Proceedings of the 17th ACM International Symposium on Nanoscale Architectures  ·  07 Dec 2022  ·  doi:10.1145/3565478.3572544
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual  ·  16 Oct 2022  ·  [no id info]
Falcon: Fast Spectral Inference on Encrypted Data
Falcon: Fast Spectral Inference on Encrypted Data
Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual  ·  16 Oct 2022  ·  [no id info]
AutoQ: Automated Kernel-Wise Neural Network Quantization
AutoQ: Automated Kernel-Wise Neural Network Quantization
8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020  ·  16 Oct 2022  ·  [no id info]
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual  ·  16 Oct 2022  ·  [no id info]
SAFENet: A Secure, Accurate and Fast Neural Network Inference
SAFENet: A Secure, Accurate and Fast Neural Network Inference
9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021  ·  16 Oct 2022  ·  [no id info]
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event  ·  16 Oct 2022  ·  [no id info]
MATCHA: A Fast and Energy-Efficient Accelerator for Fully Homomorphic Encryption over the Torus
MATCHA: A Fast and Energy-Efficient Accelerator for Fully Homomorphic Encryption over the Torus
Proceedings of the 59th Annual Design Automation Conference 2019, DAC 2022, San Francisco, CA, from July 11–15, 2022  ·  16 Oct 2022  ·  [no id info]
Lite-MDETR: A Lightweight Multi-Modal Detector
Lite-MDETR: A Lightweight Multi-Modal Detector
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  ·  16 Oct 2022  ·  [no id info]
Language model compression with weighted low-rank factorization
Language model compression with weighted low-rank factorization
International Conference on Learning Representations  ·  16 Oct 2022  ·  [no id info]
DictFormer: Tiny Transformer with Shared Dictionary
DictFormer: Tiny Transformer with Shared Dictionary
International Conference on Learning Representations  ·  16 Oct 2022  ·  [no id info]
coxHE: A software hardware co-design framework for FPGA acceleration of homomorphic computation
coxHE: A software hardware co-design framework for FPGA acceleration of homomorphic computation
2022 Design, Automation & Test in Europe Conference & Exhibition, DATE 2022, Virtual, March 14-23, 2022  ·  15 Oct 2022  ·  [no id info]

2021

Automatic Mixed-Precision Quantization Search of BERT
Automatic Mixed-Precision Quantization Search of BERT
Changsheng Zhao, Ting Hua, Yilin Shen, Qian Lou, Hongxia Jin
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence  ·  01 Aug 2021  ·  doi:10.24963/ijcai.2021/472
CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRU
CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRU
Bo Feng, Qian Lou, Lei Jiang, Geoffrey Fox
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing  ·  01 Jan 2021  ·  doi:10.18653/v1/2021.emnlp-main.156

2020

Helix
Helix
Qian Lou, Sarath Chandra Janga, Lei Jiang
Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques  ·  30 Sep 2020  ·  doi:10.1145/3410463.3414626
LightBulb: A Photonic-Nonvolatile-Memory-based Accelerator for Binarized Convolutional Neural Networks
LightBulb: A Photonic-Nonvolatile-Memory-based Accelerator for Binarized Convolutional Neural Networks
Farzaneh Zokaee, Qian Lou, Nathan Youngblood, Weichen Liu, Yiyuan Xie, Lei Jiang
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)  ·  01 Mar 2020  ·  doi:10.23919/DATE48585.2020.9116494
MindReading: An Ultra-Low-Power Photonic Accelerator for EEG-based Human Intention Recognition
MindReading: An Ultra-Low-Power Photonic Accelerator for EEG-based Human Intention Recognition
Qian Lou, Wenyang Liu, Weichen Liu, Feng Guo, Lei Jiang
2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC)  ·  01 Jan 2020  ·  doi:10.1109/ASP-DAC47756.2020.9045333

2019

Transactional Memory Scheduling Using Machine Learning Techniques
Transactional Memory Scheduling Using Machine Learning Techniques
Basem Assiri, Costas Busch, Mansour Al Ghanim
International Journal of P2P Network Trends and Technology  ·  25 Aug 2019  ·  doi:10.14445/22492615/ijptt-v9i4p404
HolyLight: A Nanophotonic Accelerator for Deep Learning in Data Centers
HolyLight: A Nanophotonic Accelerator for Deep Learning in Data Centers
Weichen Liu, Wenyang Liu, Yichen Ye, Qian Lou, Yiyuan Xie, Lei Jiang
2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)  ·  01 Mar 2019  ·  doi:10.23919/DATE.2019.8715195

2018

3DICT
3DICT
Qian Lou, Wujie Wen, Lei Jiang
Proceedings of the International Conference on Computer-Aided Design  ·  05 Nov 2018  ·  doi:10.1145/3240765.3240767
BRAWL: A Spintronics-Based Portable Basecalling-in-Memory Architecture for Nanopore Genome Sequencing
BRAWL: A Spintronics-Based Portable Basecalling-in-Memory Architecture for Nanopore Genome Sequencing
Qian Lou, Lei Jiang
IEEE Computer Architecture Letters  ·  01 Jul 2018  ·  doi:10.1109/LCA.2018.2882384

2017

Runtime and reconfiguration dual-aware placement for SRAM-NVM hybrid FPGAs
Runtime and reconfiguration dual-aware placement for SRAM-NVM hybrid FPGAs
Qian Lou, Mengying Zhao, Lei Ju, Chun Jason Xue, Jingtong Hu, Zhiping Jia
2017 IEEE 6th Non-Volatile Memory Systems and Applications Symposium (NVMSA)  ·  01 Aug 2017  ·  doi:10.1109/NVMSA.2017.8064477