Backdoor Mitigation via Adversarial Training Techniques
Talk, AIRS, Shenzhen, China
Introduce the my recent work for Backdoor defense Published in NeurIPS 2023. Slides are available here.
Talks and presentations
Advanced Works in ICCV 2023: Backdoor Learning I
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the Advanced Works in ICCV 2023: Backdoor Learning I. Slides are available here.
Tutorial on Backdoor Learning: Recent Advances and Future Trends
Tutorial, ICCV 2023, Pairs, France
The Tutorial for Backdoor learning in ICCV. Slides are available here.
Structured Pruning of Deep Convolutional Neural Networks
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the Structured Pruning of Deep Convolutional Neural Networks. Slides are available here.
Sharpness-Aware Minimization
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the Sharpness-Aware Minimization (SAM) and its applications to model robustness. Slides are available here.
Improving Robustness using Generated Data
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce how to improve robustness using Generated Data. Slides are available here.
Loss Surfaces, Mode Connectivity and Model Robustness
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the loss landscape of the machine learning model and its application to improve model robustness. Specifically, we discuss the mode connectivity, the loss landscape property of the poisoned model, and the existence of the Trojan model. Slides are available here.
Distributionally Robust Learning
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the background, formulation, methods and applications of Distributionally Robust Learning. Slides are available here.
On the Tradeoff between Fairness and Robustness
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce some works about the tradeoff between fairness and robustness. Slides are available here.
Energy-based Learning for Cooperative Games in Valuation Problems
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce cooperative/non-cooperative games, valuation problem and the application of energy-based model in valuation problem. Slides are available here.
Generative Models
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the background, formulations, methods and applications of generative models, including VAE and variants of GAN. Slides are available here.
Bias and Fairness in Machine Learning
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce the background, notions, methods and applications of fairness in Machine Learning. Slides are available here.
Solving Mixed Integer Programs Using Neural Networks
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce and discuss the work “Solving Mixed Integer Programs Using Neural Networks”. Slides are available here.
Logarithmic Regret Algorithms for Online Convex Optimization
Weekly Talk, CUHKSZ, Shenzhen, China
Introduce some logarithmic regret algorithms for Online Convex Optimization problems. Slides are available here.