2026
arXiv preprint
Taming Outlier Tokens in Diffusion Transformers
Dual-Stage Registers reduce harmful outlier tokens in both vision encoders and diffusion transformers, improving generation quality across ImageNet and text-to-image settings.
Research
I study privacy, security, and copyright questions in generative models, alongside practical methods for making diffusion models more reliable. My recent work focuses on data extraction, machine unlearning, membership inference, and representation-space generation.
Google Scholar2026
KDD 2026
Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
We identify a corruption stage during few-shot diffusion fine-tuning and use Bayesian neural networks to improve fidelity, quality, and diversity without extra inference cost.
2025
NeurIPS 2025
Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
Exact unlearning can still leak removed examples when pre- and post-unlearning models are exposed; our guided attack doubles extraction success in some settings.
2025
TPDP 2025
Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
A lightweight learned membership inference attack reveals privacy leakage in diffusion-based tabular synthesis and won all four tracks of the MIDST Challenge.
2025
ICML 2025
Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models
FineXtract uses the distribution shift between pretrained and personalized diffusion models to recover about 20% of fine-tuning data from real-world checkpoints.
2025
ICLR 2025 (Spotlight)
Targeted Attack Improves Protection against Unauthorized Diffusion Customization
Carefully selected targeted attacks provide stronger protection against unauthorized diffusion customization than untargeted adversarial watermarks.
2024
CVPR 2024
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
CGI-DM visualizes conceptual differences between pretrained and fine-tuned diffusion models to provide evidence for copyright authentication.
2023
ICML 2023 (Oral)
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
AdvDM uses adversarial examples as protective watermarks that prevent diffusion models from learning an artist's style from unauthorized images.
2023
arXiv preprint
Mist: Towards Improved Adversarial Examples for Diffusion Models
Mist improves the transferability and robustness of adversarial watermarks designed to protect artwork from unauthorized diffusion-model imitation.