Publications

2025

  1. arXiv
    Judging with Confidence: Calibrating Autoraters to Preference Distributions
    Zhuohang Li, Xiaowei Li, Chengyu Huang, and 11 more authors
    arXiv preprint arXiv:2510.00263, 2025
  2. NeurIPS
    What Really is a Member? Discrediting Membership Inference via Poisoning
    Neal Mangaokar, Ashish Hooda, Zhuohang Li, and 5 more authors
    Advances in Neural Information Processing Systems, 2025
  3. EMNLP
    Towards Statistical Factuality Guarantee for Large Vision-language Models
    Zhuohang Li, Chao Yan, Nicholas Jackson, and 4 more authors
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
  4. ACL
    SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization
    Wendi Cui, Jiaxin Zhang, Zhuohang Li, and 5 more authors
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
  5. ACL
    Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey
    Wendi Cui, Jiaxin Zhang, Zhuohang Li, and 5 more authors
    In Findings of the Association for Computational Linguistics, 2025
  6. JAMIA
    Large Language Models are Less Effective at Clinical Prediction Tasks than Locally Trained Machine Learning Models
    Katherine E Brown, Chao Yan, Zhuohang Li, and 7 more authors
    Journal of the American Medical Informatics Association, 2025

2024

  1. EMNLP
    Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
    Zhuohang Li, Jiaxin Zhang, Chao Yan, and 4 more authors
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
  2. EMNLP
    Divide-Conquer-Reasoning for Consistency Evaluation and Automatic Improvement of Large Language Models
    Wendi Cui, Zhuohang Li, Damien Lopez, and 4 more authors
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, 2024
  3. CCS
    Analyzing Inference Privacy Risks Through Gradients In Machine Learning
    Zhuohang Li, Andrew Lowy, Jing Liu, and 4 more authors
    In Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security, 2024
  4. AMIA
    Optimizing Large Language Models for Discharge Prediction: Best Practices in Leveraging Electronic Health Record Audit Logs
    Xinmeng Zhang, Chao Yan, Yuyang Yang, and 4 more authors
    In American Medical Informatics Association Annual Symposium, 2024
  5. BMVC
    Transferable Learned Image Compression-Resistant Adversarial Perturbations
    Yang Sui, Zhuohang Li, Ding Ding, and 4 more authors
    In British Machine Vision Conference, 2024
  6. JMIR
    Generating Synthetic Electronic Health Record Data Using Generative Adversarial Networks: Tutorial
    Chao Yan, Ziqi Zhang, Steve Nyemba, and 1 more author
    Journal of Medical Internet Research, 2024
  7. PhaseEvo: Towards Unified Long-Context Prompt Optimization for Large Language Models
    Wendi Cui, Jiaxin Zhang, Zhuohang Li, and 5 more authors
    ICML Workshop on Long-Context Foundation Models, 2024

2023

  1. Why Does Differential Privacy with Large Epsilon Defend Against Practical Mem- bership Inference Attacks?
    Andrew Lowy, Zhuohang Li, Jing Liu, and 3 more authors
    AAAI Workshop on Privacy-Preserving Artificial Intelligence, 2023
  2. EMNLP
    SAC^3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
    Jiaxin Zhang, Zhuohang Li, Kamalika Das, and 2 more authors
    In Findings of Empirical Methods in Natural Language Processing, 2023
  3. Exploring User-level Gradient Inversion with a Diffusion Prior
    Zhuohang Li, Andrew Lowy, Jing Liu, and 4 more authors
    International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS, 2023
  4. A Divide-Conquer-Reasoning Approach to Consistency Evaluation and Improvement in Blackbox Large Language Models
    Wendi Cui, Jiaxin Zhang, Zhuohang Li, and 4 more authors
    NeurIPS Workshop on Socially Responsible Language Modelling Research, 2023
  5. NeurIPS
    Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
    Jiaxin Zhang, Zhuohang Li, Kamalika Das, and 1 more author
    Advances in Neural Information Processing Systems, 2023
  6. AMIA
    Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics
    Zhuohang Li, Chao Yan, Xinmeng Zhang, and 4 more authors
    In American Medical Informatics Association Annual Symposium, 2023
  7. Reconstruction Distortion of Learned Image Compression with Imperceptible Perturbations
    Yang Sui, Zhuohang Li, Ding Ding, and 4 more authors
    ICML Neural Compression Workshop, 2023
  8. ICASSP
    Speech Privacy Leakage from Shared Gradients in Distributed Learning
    Zhuohang Li, Jiaxin Zhang, and Jian Liu
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
  9. AsiaCCS
    RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
    Yue Cui, Syed Irfan Ali Meerza, Zhuohang Li, and 3 more authors
    In Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, 2023

2022

  1. CCS
    HeatDeCam: Detecting Hidden Spy Cameras via Thermal Emissions
    Zhiyuan Yu, Zhuohang Li, Yuanhaur Chang, and 3 more authors
    In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022
  2. MobiCom
    Audio-domain Position-independent Backdoor Attack via Unnoticeable Triggers
    Cong Shi, Tianfang Zhang, Zhuohang Li, and 6 more authors
    In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, 2022
  3. ECCV
    RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
    Huy Phan, Cong Shi, Yi Xie, and 7 more authors
    In Proceedings of 17th European Conference on Computer Vision, 2022
  4. EMBC
    Fair and Privacy-Preserving Alzheimer’s Disease Diagnosis Based on Spontaneous Speech Analysis via Federated Learning
    Syed Irfan Ali Meerza, Zhuohang Li, Luyang Liu, and 2 more authors
    In Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2022
  5. EMBC
    Privacy-preserving Speech-based Depression Diagnosis via Federated Learning
    Yue Cui, Zhuohang Li, Luyang Liu, and 2 more authors
    In Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2022
  6. CVPR
    Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage
    Zhuohang Li, Jiaxin Zhang, Luyang Liu, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  7. GetMobile
    BioFace-3D: 3D Facial Tracking and Animation via Single-ear Wearable Biosensors
    Yi Wu, Vimal Kakaraparthi, Zhuohang Li, and 3 more authors
    GetMobile: Mobile Computing and Communications, 2022

2021

  1. CCS
    Robust Detection of Machine-induced Audio Attacks in Intelligent Audio Systems with Microphone Array
    Zhuohang Li, Cong Shi, Tianfang Zhang, and 4 more authors
    In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2021
  2. ICPADS
    Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updates
    Zhuohang Li, Luyang Liu, Jiaxin Zhang, and 1 more author
    In 2021 IEEE 27th International Conference on Parallel and Distributed Systems, 2021
  3. ACSAC
    Time to Rethink the Design of Qi Standard? Security and Privacy Vulnerability Analysis of Qi Wireless Charging
    Yi Wu, Zhuohang Li, Nicholas Van Nostrand, and 1 more author
    In Annual Computer Security Applications Conference, 2021
  4. MobiCom
    BioFace-3D: Continuous 3d Facial Reconstruction through Lightweight Single-ear Biosensors
    Yi Wu, Vimal Kakaraparthi, Zhuohang Li, and 3 more authors
    In Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, 2021
  5. JSPS
    Real-time, Robust and Adaptive Universal Adversarial Attacks against Speaker Recognition Systems
    Yi Xie, Zhuohang Li, Cong Shi, and 3 more authors
    Springer Journal of Signal Processing Systems, 2021
  6. AAAI
    Enabling Fast and Universal Audio Adversarial Attack Using Generative Model
    Yi Xie, Zhuohang Li, Cong Shi, and 3 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2021

2020

  1. CCS
    AdvPulse: Universal, Synchronization-free, and Targeted Audio Adversarial Attacks via Subsecond Perturbations
    Zhuohang Li, Yi Wu, Jian Liu, and 2 more authors
    In Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020
  2. ICASSP
    Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
    Yi Xie, Cong Shi, Zhuohang Li, and 3 more authors
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2020
  3. HotMobile
    Practical Adversarial Attacks Against Speaker Recognition Systems
    Zhuohang Li, Cong Shi, Yi Xie, and 3 more authors
    In Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications, 2020