Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Kah-Kay SungSuggested from co-authorship
- Chew Lim TanSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works156 from public data
- Deep Polarized Network for Supervised Learning of Accurate Binary Hashing Codes148
A novel deep polarized network (DPN) for learning to hash is proposed, in which each channel in the network outputs is pushed far away from zero by employing a differentiable bit-wise hinge-like loss which is dubbed as polarization loss.
- FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models123
FATE-LLM facilitates federated learning for large language models (coined FedLLM), promotes efficient training of Fed LLM using parameter-efficient fine-tuning methods, protects the intellectual property of LLMs, and preserves data privacy during training and inference through privacy-preserving mechanisms.
- Object Detection in Equirectangular Panorama114
A high-resolution equirectangular panorama dataset for object detection and a multi-projection variant of the YOLO detector, which outperforms the other state-of-the-art detector, Faster R-CNN, and achieves the best accuracy with low-resolution input.
- FedIPR: Ownership Verification for Federated Deep Neural Network Models106
A novel federated deep neural network (FedDNN) ownership verification scheme that allows private watermarks to be embedded and verified to claim legitimate IPR of FedDNN models and is resilient to various federated training settings and robust against removal attacks.
- FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning104
FEDCG is proposed, a novel federated learning method that leverages conditional generative adversarial networks to achieve high-level privacy protection while still maintaining competitive model performance and privacy analysis shows that FEDCG has a high- level privacy-preserving capability.
- 95
- Trading Off Privacy, Utility, and Efficiency in Federated Learning91
This work analyzes the lower bounds for the privacy leakage, utility loss, and efficiency reduction for several widely-adopted protection mechanisms, including Randomization, Homomorphic Encryption, Secret Sharing, and Compression, and proposes a unified federated learning framework that reconciles horizontal and vertical federation learning.
- No Free Lunch Theorem for Security and Utility in Federated Learning89
A general framework is illustrated that formulates the trade-off between privacy loss and utility loss from a unified information-theoretic point of view, and delineates quantitative bounds of the privacy-utility trade-offs when different protection mechanisms including randomization, sparsity, and homomorphic encryption are used.
- 89
- Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attacks88
A complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs is presented and it is shown that the proposed method does not compromise the original GAns performance, and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks.
- FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model85
FedTracker is presented, the first FL model protection framework that provides both ownership verification and traceability and is effective in ownership verification, traceability, and maintains good fidelity and robustness against various watermark removal attacks.
- Federated Learning with Privacy-preserving and Model IP-right-protection76
FedIPR, a novel ownership verification scheme, is introduced by embedding watermarks into FL models to verify the ownership of FL models and protect model intellectual property rights (IPR or IP-right for short).
- Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks73
This paper investigates capabilities of Privacy-Preserving Deep Learning mechanisms against various forms of privacy attacks, and proposes to quantitatively measure the trade-off between model accuracy and privacy losses incurred by reconstruction, tracing and membership attacks.
- Ten Challenging Problems in Federated Foundation Models64
This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency.
- 64
- Urban 3D segmentation and modelling from street view images and LiDAR point clouds58
A novel methodology that takes GPS registered LiDAR point clouds and street view images as inputs and creates semantic labels for the 3D points clouds using a hybrid of rule-based parsing and learning-based labelling that combine point cloud and photometric features is proposed.
- 55
- 53
- Federated Learning with Quantum Secure Aggregation52
It was empirically demonstrated that the proposed QSA can be readily applied to aggregate different types of local models including logistic regression, convolutional neural networks (CNN) as well as quantum neural network (QNN), indicating the versatility of the QSA scheme.
- Protect, show, attend and tell: Empowering image captioning models with ownership protection51
This work is the first to propose ownership protection on image captioning task and studies and proposes two different embedding schemes in the hidden memory state of a recurrent neural network to protect the image Captioning model.
- A Hybrid Self-Supervised Learning Framework for Vertical Federated Learning38
This work proposes a Federated Hybrid Self-Supervised Learning framework, named FedHSSL, that utilizes cross-party views of samples aligned among parties and local views of unaligned samples within each party to improve the representation learning capability of the VFL joint model.
- 38
- 37
- Fast Registration for Cross-Source Point Clouds by using Weak Regional Affinity and Pixel-Wise Refinement36
Two components, the weak region affinity and pixel-wise refinement, are proposed to maintain the global and local information of 3D point clouds and integrated into an iterative tensor-based registration algorithm to solve the cross-source point cloud registration problem.
- SecureBoost$$+$$: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree34
This work proposes SecureBoost+, a large-scale and high-performance vertical federated gradient boosting decision tree framework that achieves high performance through several novel optimizations for SecureBoost, including ciphertext operation optimization, the introduction of new training mechanisms, and multi-classification training optimization.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.