Kaijing Luo

ORCID: 0009-0005-9798-8098
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • AI in cancer detection
  • Domain Adaptation and Few-Shot Learning
  • Music and Audio Processing
  • COVID-19 diagnosis using AI
  • Advanced Steganography and Watermarking Techniques
  • Speech Recognition and Synthesis
  • Radiomics and Machine Learning in Medical Imaging
  • Advanced Neural Network Applications
  • Privacy-Preserving Technologies in Data
  • Speech and Audio Processing
  • Cryptography and Data Security
  • Machine Learning and Data Classification

University of Electronic Science and Technology of China
2023

Protecting intellectual property (IP) in federated learning (FL) is increasingly important as clients contribute proprietary data to collaboratively train models. Model watermarking, particularly through backdoor-based methods, has emerged a popular approach for verifying ownership and contributions deep neural networks trained via FL. By manipulating their datasets, can embed secret pattern, resulting non-intuitive predictions that serve proof of participation, useful claiming incentives or...

10.48550/arxiv.2410.21179 preprint EN arXiv (Cornell University) 2024-10-28

Pneumonia is an important threat to human health, and different types of pneumonia have treatment options, so the prediction classification are health issues. In this paper, chest X-ray images used as data, final ensemble model can achieve excellent performance on these two tasks. addition, paper introduces InceptionNeXt problems for first time, finds that convolution kernels perception fields may be more suitable medical image research

10.1145/3625403.3625415 article EN 2023-09-15
Coming Soon ...