Publications
2025
- NeurIPSWhat Really is a Member? Discrediting Membership Inference via PoisoningAdvances in Neural Information Processing Systems, 2025
- EMNLPTowards Statistical Factuality Guarantee for Large Vision-language ModelsIn Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
- ACLSEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt OptimizationIn Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
- ACLHeuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A SurveyIn Findings of the Association for Computational Linguistics, 2025
- JAMIALarge Language Models are Less Effective at Clinical Prediction Tasks than Locally Trained Machine Learning ModelsJournal of the American Medical Informatics Association, 2025
2024
- EMNLPDo You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented GenerationIn Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
- EMNLPDivide-Conquer-Reasoning for Consistency Evaluation and Automatic Improvement of Large Language ModelsProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, 2024
- CCSAnalyzing Inference Privacy Risks Through Gradients In Machine LearningIn Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security, 2024
- AMIAOptimizing Large Language Models for Discharge Prediction: Best Practices in Leveraging Electronic Health Record Audit LogsIn American Medical Informatics Association Annual Symposium, 2024
- BMVCTransferable Learned Image Compression-Resistant Adversarial PerturbationsIn British Machine Vision Conference, 2024
- JMIRGenerating Synthetic Electronic Health Record Data Using Generative Adversarial Networks: TutorialJournal of Medical Internet Research, 2024
- PhaseEvo: Towards Unified Long-Context Prompt Optimization for Large Language ModelsICML Workshop on Long-Context Foundation Models, 2024
2023
- Why Does Differential Privacy with Large Epsilon Defend Against Practical Mem- bership Inference Attacks?AAAI Workshop on Privacy-Preserving Artificial Intelligence, 2023
- EMNLPSAC^3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check ConsistencyIn Findings of Empirical Methods in Natural Language Processing, 2023
- Exploring User-level Gradient Inversion with a Diffusion PriorInternational Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS, 2023
- A Divide-Conquer-Reasoning Approach to Consistency Evaluation and Improvement in Blackbox Large Language ModelsNeurIPS Workshop on Socially Responsible Language Modelling Research, 2023
- NeurIPSInteractive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human SupervisionAdvances in Neural Information Processing Systems, 2023
- AMIASplit Learning for Distributed Collaborative Training of Deep Learning Models in Health InformaticsIn American Medical Informatics Association Annual Symposium, 2023
- Reconstruction Distortion of Learned Image Compression with Imperceptible PerturbationsICML Neural Compression Workshop, 2023
- ICASSPSpeech Privacy Leakage from Shared Gradients in Distributed LearningIn Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
- AsiaCCSRecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy DefenseIn Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, 2023
2022
- CCSHeatDeCam: Detecting Hidden Spy Cameras via Thermal EmissionsIn Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022
- MobiComAudio-domain Position-independent Backdoor Attack via Unnoticeable TriggersIn Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, 2022
- ECCVRIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNNIn Proceedings of 17th European Conference on Computer Vision, 2022
- EMBCFair and Privacy-Preserving Alzheimer’s Disease Diagnosis Based on Spontaneous Speech Analysis via Federated LearningIn Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2022
- EMBCPrivacy-preserving Speech-based Depression Diagnosis via Federated LearningIn Proceedings of 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2022
- CVPRAuditing Privacy Defenses in Federated Learning via Generative Gradient LeakageIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
- GetMobileBioFace-3D: 3D Facial Tracking and Animation via Single-ear Wearable BiosensorsGetMobile: Mobile Computing and Communications, 2022
2021
- CCSRobust Detection of Machine-induced Audio Attacks in Intelligent Audio Systems with Microphone ArrayIn Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2021
- ICPADSByzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model UpdatesIn 2021 IEEE 27th International Conference on Parallel and Distributed Systems, 2021
- ACSACTime to Rethink the Design of Qi Standard? Security and Privacy Vulnerability Analysis of Qi Wireless ChargingIn Annual Computer Security Applications Conference, 2021
- MobiComBioFace-3D: Continuous 3d Facial Reconstruction through Lightweight Single-ear BiosensorsIn Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, 2021
- JSPSReal-time, Robust and Adaptive Universal Adversarial Attacks against Speaker Recognition SystemsSpringer Journal of Signal Processing Systems, 2021
- AAAIEnabling Fast and Universal Audio Adversarial Attack Using Generative ModelIn Proceedings of the AAAI Conference on Artificial Intelligence, 2021
2020
- CCSAdvPulse: Universal, Synchronization-free, and Targeted Audio Adversarial Attacks via Subsecond PerturbationsIn Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020
- ICASSPReal-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition SystemsIn Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2020
- HotMobilePractical Adversarial Attacks Against Speaker Recognition SystemsIn Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications, 2020