3 papers
cs.CV2024
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
Namhyuk Ahn, KiYoon Yoo, Wonhyuk Ahn +2
Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection met…
cs.CV2024
Imperceptible Protection against Style Imitation from Diffusion Models
Namhyuk Ahn, Wonhyuk Ahn, KiYoon Yoo +2
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 int…
cs.CL2023
Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
KiYoon Yoo, Wonhyuk Ahn, Nojun Kwak
We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection…