3 papers
cs.CV2026
Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
Yeonghwan Song, Chanhui Lee, Jinsoo Park +1
Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propos…
cs.CV2026
Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
Chanhui Lee, Donggyu Choi, Seunghyun Shin +2
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, adv…
cs.CV2025
Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
Chanhui Lee, Yeonghwan Song, Jeany Son
Data-free Universal Adversarial Perturbation (UAP) is an image-agnostic adversarial attack that deceives deep neural networks using a single perturbation generated solely from rand…