Institution profile

Inha University

Academic institutionasia · kr
Official website
Research library117linked papers
Opportunities0open roles
Selected work

Representative Papers

Imperceptible Protection against Style Imitation from Diffusion Models

Mar 28, 2024arXiv.org

To address copyright infringement and artistic style appropriation risks posed by diffusion models, this paper proposes a visually lossless copyright protection method. The approach comprises three key contributions: (1) perception-sensitive map-guided instance-aware fine-tuning, enabling fine-grained stylistic perturbation; (2) difficulty-aware dynamic intensity modulation, which adaptively adjusts perturbation magnitude based on the sample’s stylistic mimicability; and (3) a multi-scale perceptual constraint library, jointly optimizing defense robustness and image fidelity. Without introducing perceptible visual artifacts, the method achieves over 92% style imitation suppression, reduces LPIPS by 41%, and improves FID by 27%, significantly outperforming existing state-of-the-art methods.

7 citationsRead paper

Nonparametric estimation of a factorizable density using diffusion models

Jan 03, 2025

To address the curse of dimensionality in high-dimensional nonparametric density estimation, this paper considers densities exhibiting a low-dimensional factorized structure—i.e., statistical independence across variable groups. We propose diffusion models as implicit density estimators and, for the first time within a statistical framework, establish that under the factorization assumption, the resulting estimator achieves a dimension-free minimax-optimal convergence rate in total variation distance—thereby circumventing the curse of dimensionality. To explicitly encode structural priors, we design a sparse weight-sharing neural network architecture that adaptively models low-dimensional components. Theoretical analysis confirms the improved statistical efficiency, while empirical results demonstrate superior estimation accuracy and enhanced interpretability in high-dimensional sparse settings—all without sacrificing the flexibility inherent to nonparametric methods.

4 citations1 influentialRead paper
Recent publications

Latest Papers

Erdős-Pósa property for induced packings of long $S$-cycles

Aug 23, 2026

本文解决了长S-圈的诱导装包问题,通过引入基于脆弱耳的新耳分解技术,证明了存在多项式函数f(k, l),使得每个图要么包含k个长度至少为l的S-圈的诱导装包,要么存在至多f(k, l)个顶点的集合与所有长度至少为l的S-圈相交。

0 citationsRead paper