Qian Lou
 |
Director of A³ Lab at UCF and Assistant Professor |
Publications | Research Group | Teaching | Google Scholar | Patents
Qian Lou directs the A³ Lab at UCF and is a tenure-track assistant professor in Computer Science. He has published 50+ papers in top ML/AI/NLP/CV venues and leading security/systems venues. His research has been supported by major federal programs (e.g., NSF and DoD). He mentors multiple productive and collaborative Ph.D. students and supports student internships and career development. He teaches graduate-level courses and contributes sustained professional service, including area chair roles for major ML venues (e.g., NeurIPS, ICLR, ACL) and TPC/PC service for top security/systems venues (e.g., CCS, NDSS, DAC, ISCA).
A³ Lab — Evaluation, Design, and Applications for Agentic AI. Our mission is to build Intelligent, efficient, and safe Agentic AI—AI systems that can plan, use tools, and act reliably under real-world constraints. We start from real applications and measurable evidence: datasets, evaluation workflows, and benchmarks that expose practical failure modes and bottlenecks. These takeaways directly motivate and guide our designs across model, I/O, and system layers.
- (1) Agentic AI Evaluation & Applications (datasets, workflows, and benchmarks): We curate domain datasets and develop data curation and synthesis pipelines (including privacy-preserving generation) for high-impact applications such as coding, research automation, healthcare, and quantum. We build end-to-end evaluation workflows and define metrics to benchmark agent behavior and failure modes, including tool-use correctness, robustness, safety/policy compliance, privacy leakage, and cost/latency. These measurements provide real-world analysis, actionable takeaways, and concrete requirements for trustworthy agents.
- (2) Agentic AI Design (efficiency, safety, and security by construction): Guided by evaluation-driven requirements, we design agentic AI systems across three layers: Model-level optimizations (efficiency- and security-aware training/inference, compression and pruning), I/O-level design (compression, monitoring, copyright/provenance, and certification for efficient and safe interactions), and System-level security (using cryptographic tools such as FHE/MPC/ZK and trusted hardware (TEEs) to protect agent data, models, and tool execution). We further apply system-aware optimization to achieve strong guarantees with near-native performance.
News
| 01 / 2026 | [Paper] | One paper has been accepted by ICLR 2026. |
| 12 / 2025 | [Paper] | One paper has been accepted by ASPLOS 2026. |
| 11 / 2025 | [Paper] | One paper has been accepted by PETS 2026. |
| 10 / 2025 | [Paper] | One paper has been accepted by NDSS 2026. |
| 09 / 2025 | [Paper][Mentoring] | Our federated learning with encrypted aggregation (<2x overhead) is accepted by NeurIPS 2025. |
| 08 / 2025 | [Grant] | Our privacy-preserving data synthesis based on private computing is funded by NSF SaTC Crosscutting. |
| 08 / 2025 | [Paper][Mentoring] | Two papers are accepted by EMNLP 2026. |
| 04 / 2025 | [Grant] | Our LLM Application Security Testing (LAST) Framework is funded by the DoD Pathfinder Program. |
| 03 / 2025 | [Grant] | Our system support for secure computing is funded by NSF CISE Core. |
| 02 / 2025 | [Paper] | One paper is accepted by DAC 2025. |
| 01 / 2025 | [Paper] | One paper is accepted by ICLR 2025. |
| 10 / 2024 | [Paper] | One paper is accepted by NeurIPS 2024. |
| 09 / 2024 | [Paper] | Two papers about Jailbreaking and fairness backdoors are accepted by EMNLP 2024. |
| 09 / 2024 | [Paper] | DataSeal is accepted by IEEE S&P 2025. |
| 07 / 2024 | [Paper] | One paper is accepted by MICRO 2024. |
| 07 / 2024 | [Paper] | WBP is accepted by ECCV 2024. |
| 07 / 2024 | [Paper] | SSL-Cleanse is accepted by ECCV 2024. |
| 06 / 2024 | [Paper] | BoostCom is accepted by PACT 2024. |
| 05 / 2024 | [Mentoring] | Congratulations to Jiaqi Xue and Yancheng Zhang, who started their internships at Samsung Research America. |
| 05 / 2024 | [Paper] | CR-UTP is accepted by ACL 2024. |
| 03 / 2024 | [Paper] | TrojFSP is accepted by NAACL 2024 (Oral in the main conference). |
| 09 / 2023 | [Paper] | TrojLLM is accepted by NeurIPS 2023. |
| 02 / 2023 | [Paper] | TrojViT is accepted by CVPR 2023. |
| 02 / 2023 | [Paper] | Primer is accepted by DAC 2023. |
| 01 / 2023 | [Paper] | TrojText is accepted by ICLR 2023. |
| 10 / 2022 | [Paper] | Weighted value decomposition on language model is accepted by EMNLP 2022. |
| 03 / 2022 | [Paper] | LITE-MDETR is accepted by CVPR 2022. |
| 02 / 2022 | [Paper] | MATCHA is accepted by DAC 2022. |
| 01 / 2022 | [Paper] | Language Model Compression is accepted by ICLR 2022. |
| 01 / 2022 | [Paper] | DictFormer is accepted by ICLR 2022. |
| 08 / 2021 | [Paper] | CryptoGRU is accepted by EMNLP 2021. |
| 05 / 2021 | [Paper] | HEMET is accepted by ICML 2021. |
| 05 / 2021 | [Research] | Qian received a Luddy Outstanding Research Award. |
| 09 / 2020 | [Paper] | Three papers were accepted by NeurIPS 2020. |
Research Group
We are a collaborative team.
Prospective Students: We are recruiting Ph.D. students and a postdoctoral researcher to join the A³ Lab at UCF. Interested applicants should email qian.lou@ucf.edu with the subject line: “2026 Prospective Member – A³ Lab at UCF”. Please include your CV and a brief summary of your research experience, interests, and notable accomplishments. For application details, please apply through the CS department and include my name as a possible advisor in your application.
Have questions? Check out my answers to the PhD Advisor Guide.
Recent Community Services
NSF: Panelist
ICLR 2026: Area Chair
NeurIPS 2025: Area Chair
CCS 2026: Program Committee
NDSS 2026: Program Committee
GLSVLSI 2025: Track Chair
ISCA: Program Committee
DAC: Technical Program Committee
ISCA 2023: Local Area Chair
Tiny and Fair ML Design Contest Organizer at ESWEEK 2023
IEEE Transactions on Information Forensics and Security: Reviewer
AI for Content Creation (AI4CC) Workshop @ CVPR 2024: Area Chair
AAAI: Senior Program Committee
NeurIPS: Reviewer
ICML: Reviewer
ACL/NAACL: Reviewer
ICLR: Reviewer
CVPR: Reviewer
ECCV: Reviewer
Teaching
2022 Fall: CDA 5106 Advanced Computer Architecture
2023 Spring: CAP 6614 Current Topics in Machine Learning
2023 Fall: CDA 5106 Advanced Computer Architecture
2024 Spring: CAP 6614 Current Topics in Machine Learning
2025 Spring: CAP 6614 Current Topics in Machine Learning
Publications
Publications at UCF
* indicates students and staff under my supervision[ICLR 26] TFHE-Coder: Evaluating LLM Agents for secure Fully Homomorphic Encryption Code Generation |
[PoPETs 26] SoK: Can Fully Homomorphic Encryption Support General AI Computation? A Functional and Cost Analysis |
[SaTML 26] RobPI: Robust Private Inference against Malicious Client |
[NeurIPS 25] DictPFL: Efficient and Private Federated Learning on Encrypted Gradients |
[EMNLP 25] Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations |
[EMNLP 25] Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts |
[DAC 25] zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing |
[ICLR 25] CipherPrune: Efficient and Scalable Private Transformer Inference |
[S&P 25] DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data |
[NeurIPS 24] HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning |
[EMNLP 24] BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers |
[EMNLP 24] Jailbreaking LLMs with Arabic Transliteration and Arabizi |
[MICRO 24] Trinity: A General Purpose FHE Accelerator |
[CCS-WAHC 24] HEBridge: Connecting Arithmetic and Logic Operations in FV-style HE Schemes |
[CCS-LAMPS 24] TrojFair: Trojan Fairness Attacks |
[CCS-LAMPS 24] CryptoTrain: Fast Secure Training on Encrypted Data |
[ACL 24] CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models |
[ISLPED 24] OFHE: An Electro-Optical Accelerator for Discretized TFHE |
[PACT 24] BoostCom: Towards Efficient Universal Fully Homomorphic Encryption by Boosting the Word-wise Comparisons |
[ECCV 24] WBP: Training-time Backdoor Attacks through Weight Bit Poisoning. |
[ECCV 24] SSL-Cleanse: Trojan detection and mitigation in self-supervised learning. |
[Mathematics 24] Unveiling Fall Triggers in Older Adults: A Machine Learning Graphical Model Analysis |
[NAACL 24] TrojFSP: Trojan Insertion in Few-shot Prompt Tuning |
Patents
[US20240080423A1] Fusion techniques for combining most significant bits and least significant bits of image data in image processing or other applications |
[US20230177338A1] Small and fast transformer model for multi-modal or other tasks |
[US20230104491A1] Small and fast transformer with shared dictionary |
[US20230106213A1] Machine learning model compression using weighted low-rank factorization |
[US20220121947A1] Method and system for secure, accurate and fast neural network inference |