Huming Qiu — accepted AI-conference papers

2026

DDIM Inversion as a Perturbation Amplifier: Breaking Mimicry Protection via Reconstruction Error Minimization

Huming Qiu, Peiyi Chen, Mi Zhang, Geng Hong, Xiaoyu You, Mi Wen +1

ICML 2026poster

Personalization techniques for image generation models have increasingly been misused for malicious purposes, including unauthorized style imitation and copyrighted content replication. In response, recent mimicry protection methods embed carefully designed perturbations into images to disrupt a mod…

Cited by 0 Source ↗Scholar ↗

2025

The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction

Huming Qiu, Zhaoxiang Wang, Mi Zhang, Xiaohan Zhang, Xiaoyu You, Min Yang

NeurIPS 2025poster

Image watermarking embeds imperceptible signals into AI-generated images for deepfake detection and provenance verification. Although recent semantic-level watermarking methods demonstrate strong resistance against conventional pixel-level removal attacks, their robustness against more advanced remo…

Cited by 0 Source ↗Scholar ↗