Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
This work addresses privacy and copyright concerns in generative AI by mitigating memorization in diffusion models, though it is incremental as it builds on prior insights about classifier-free guidance.
The paper tackled the problem of text-to-image diffusion models memorizing training data by showing that adjusting initial noise samples can promote earlier escape from memorization basins, reducing memorization by up to 90% while maintaining image-text alignment.
Despite their impressive generative capabilities, text-to-image diffusion models often memorize and replicate training data, prompting serious concerns over privacy and copyright. Recent work has attributed this memorization to an attraction basin-a region where applying classifier-free guidance (CFG) steers the denoising trajectory toward memorized outputs-and has proposed deferring CFG application until the denoising trajectory escapes this basin. However, such delays often result in non-memorized images that are poorly aligned with the input prompts, highlighting the need to promote earlier escape so that CFG can be applied sooner in the denoising process. In this work, we show that the initial noise sample plays a crucial role in determining when this escape occurs. We empirically observe that different initial samples lead to varying escape times. Building on this insight, we propose two mitigation strategies that adjust the initial noise-either collectively or individually-to find and utilize initial samples that encourage earlier basin escape. These approaches significantly reduce memorization while preserving image-text alignment.