2024
Defense Against Adversarial Attacks Using Topology Aligning Adversarial Training.
IEEE Trans. Inf. Forensics Secur., 2024

TraDiffusion: Trajectory-Based Training-Free Image Generation.
CoRR, 2024

UniFL: Improve Stable Diffusion via Unified Feedback Learning.
CoRR, 2024

ByteEdit: Boost, Comply and Accelerate Generative Image Editing.
CoRR, 2024

StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

ByteEdit: Boost, Comply and Accelerate Generative Image Editing.
Proceedings of the Computer Vision - ECCV 2024, 2024

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
Semantically Consistent Visual Representation for Adversarial Robustness.
IEEE Trans. Inf. Forensics Secur., 2023

DLIP: Distilling Language-Image Pre-training.
CoRR, 2023

Latent Feature Relation Consistency for Adversarial Robustness.
CoRR, 2023

CAT: Collaborative Adversarial Training.
CoRR, 2023

Improving Adversarial Robustness via Information Bottleneck Distillation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022
Towards Robust Adversarial Training via Dual-label Supervised and Geometry Constraint.
Int. J. Softw. Informatics, 2022

2019
Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing.
Proceedings of the 27th ACM International Conference on Multimedia, 2019