Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style imitation, most are accompanied by the degradation of artworks' visual quality. Recognizing the importance of maintaining this, we intro duce a visually improved protection method while preserving its protection capability. To this end, we devise a perceptual map to highlight areas sensitive to human eyes, guided by instance-aware refinement, which refines the protection intensity accordingly. We also introduce a difficulty-aware protection by predicting how difficult the artwork is to protect and dynamically adjusting the intensity based on this. Lastly, we integrate a perceptual constraints bank to further improve the imperceptibility. Results show that our method substantially elevates the quality of the protected image without compromising on protection efficacy.

Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection methods, though effective, struggle to balance protection efficacy, invisibility, and latency, thus limiting practical use. We introduce perturbation pre-training to reduce latency and propose a mixture-of-perturbations approach that dynamically adapts to input images to minimize performance degradation. Our novel training strategy computes protection loss across multiple VAE feature spaces, while adaptive targeted protection at inference enhances robustness and invisibility. Experiments show comparable protection performance with improved invisibility and drastically reduced inference time. The code and demo are available at https://webtoon.github.io/impasto

KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models.However, these contents are susceptible to illegal piracy and potential misuse without proper security measures.This calls for a secure watermarking system to guarantee copyright protection through leakage tracing or ownership identification.To effectively combat piracy and protect copyrights, a multi-bit watermarking framework should be able to embed adequate bits of information and extract the watermarks in a robust manner despite possible corruption.In this work, we explore ways to advance both payload and robustness by following a well-known proposition from image watermarking and identify features in natural language that are invariant to minor corruption.Through a systematic analysis of the possible sources of errors, we further propose a corruption-resistant infill model.Our full method improves upon the previous work on robustness by +16.8% point on average on four datasets, three corruption types, and two corruption ratios. 1

Seam carving is a representative content-aware image retargeting approach to adjust the size of an image. To preserve visually prominent content, seam-carving algorithms first calculate the connected path of pixels, referred to as the seam, according to a defined cost function and then adjust the size of an image by removing or duplicating repeatedly calculated seams. Seam carving is actively exploited to overcome diversity in the resolution of images between applications and devices; hence, detecting the distortion caused by seam carving has become important in image forensics. In this paper, we propose a convolutional neural network (CNN)-based approach to classifying seam-carving forgery. To attain the ability to learn low-level features, we designed a convolutional neural network (CNN) architecture comprising five types of network blocks specialized in capturing local artifacts caused by seam carving. An ensemble module is further adopted to both enhance performance and comprehensively analyze the features in the local areas. To validate the effectiveness of our work, extensive experiments based on various CNN-based baselines were conducted. Compared to the baselines, our work exhibits state-of-the-art performance in terms of three-class classification (original, seam inserted, and seam removed). The experimental results also demonstrate that our model with the ensemble module is robust for various unseen cases.

Content-aware image resizing is the process of adjusting the size of an image while preserving its important content. Image resizing is used to overcome diversity in resolutions between modules, such as display devices and applications, and can thus be deliberately exploited to distort or remove original content; therefore, detecting such tampering has become an important topic in forensics. This paper proposes a deep neural network architecture to capture subtle local artifacts caused by seam-based image resizing. Unlike past approaches that only classified two classes, our approach is the first attempt to solve a given forensic task with three-class classification: original, seam insertion, and seam carving. The experimental results show that our work performs better than the handcrafted feature-based method and networks designed for different forensic tasks.