Federated Learning and its security implications, particularly focusing on:
- Backdoor Attacks: Developing novel and powerful backdoor attacks to understand vulnerabilities in federated learning.
- Defense Mechanisms: Researching and designing robust defenses against backdoor attacks in federated learning settings.
- Privacy-Preserving Federated Learning: Exploring methods to enhance privacy in federated learning while maintaining model performance.
- Machine Unlearning: Investigating techniques for removing individual data from federated learning models.
- You can find my research and publications on my academic page.
- If you're interested in collaborating or discussing my research, feel free to reach out via email.
- Shiny app for visualizing and finding research papers (R Shiny): A Shiny app that enables users to search for and filter research papers sourced from platforms like IEEE Xplore, ACM, ScienceDirect, Springer, OpenReview, arXiv, DBLP, and Google Scholar.
I'm open to contributions and collaboration! If you're interested in exploring federated learning security, backdoor attacks, or other related topics, feel free to open an issue or a pull request.