Zijian Huang

[MASK] Insertion: a robust method for anti-adversarial attacks

2023

Adversarial attack aims to perturb input sequences and mislead a trained model for false predictions. To enhance the model robustness, defensing methods are accordingly employed by either data augmentation (involving adversarial samples) or model enhancement …

Understanding Generalization in Diffusion Distillation via Probability Flow Distance

2025 · ArXiv.org

Diffusion distillation provides an effective approach for learning lightweight and few-steps diffusion models with efficient generation. However, evaluating their generalization remains challenging: theoretical metrics are often impractical for high-dimensional data, while no practical metrics rigorously …