PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2607.01499v3cs.CV

Anti-Prompt: 텍스트 기반 이미지-비디오 생성에 대한 이미지 보호

Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

텍스트 기반 이미지-비디오(I2V) 생성 모델이 개인 이미지를 무단으로 애니메이션화하는 문제를 막기 위해, Anti-Prompt는 I2V 모델의 텍스트 의존성을 역이용해 디노이징 과정에서 텍스트 조건부 상호작용을 약화시키고 시각 전용 경로를 강화하는 감지 불가능한 섭동(perturbation)을 이미지에 주입한다. 두 가지 대표적인 I2V 아키텍처(full-attention, cross-attention)에서 강력한 보호 성능과 높은 전이성을 검증하였으며, Video-LLM 기반 평가 프로토콜을 통해 생성 실패를 체계적으로 진단한다.

arXiv:2602.14679v2cs.CV

Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection

Diffusion model advances have enabled powerful text-guided image editing, but also raise ethical and legal risks such as deepfakes and unauthorized use. To prevent these risks, adversarial attack-based image immunization has emerged as a promising defense against AI-driven semantic manipulation. Yet, most existing approaches require image-specific optimization or additional neural networks at inference time, hindering scalability and practicality. In this paper, we propose the first universal adversarial perturbation-based image immunization framework that generates a single, image-agnostic adversarial perturbation specifically designed for diffusion-based editing pipelines. Inspired by UAP used in targeted attacks, our method aims to generate a UAP that induces diffusion models to misinterpret the input image as a specific semantic target. Simultaneously, it suppresses original content to misdirect the model's attention during editing, thereby effectively blocking unauthorized edits by overwriting the image's original semantics via the UAP. Extensive experiments show that our method, as the first universal immunization approach, significantly outperforms several baselines in the UAP setting. Notably, despite the inherent difficulty of universal perturbations, our method achieves competitive or superior performance compared to image-specific methods under a more restricted perturbation budget, while also exhibiting strong black-box transferability across diverse diffusion models.