Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods offer a promising solution, existing finetuning-based approaches suffer from notable limitations. Anchor-free methods risk disrupting sampling trajectories, leading to visual artifacts, while anchor-based methods rely on the heuristic selection of anchor concepts. To overcome these shortcomings, we introduce a finetuning framework, dubbed ANT, which Automatically guides deNoising Trajectories to avoid unwanted concepts. ANT is built on a key insight: reversing the condition direction of classifier-free guidance during mid-to-late denoising stages enables precise content modification without sacrificing early-stage structural integrity. This inspires a trajectory-aware objective that preserves the integrity of the early-stage score function field, which steers samples toward the natural image manifold, without relying on heuristic anchor concept selection. For single-concept erasure, we propose an augmentation-enhanced weight saliency map to precisely identify the critical parameters that most significantly contribute to the unwanted concept, enabling more thorough and efficient erasure. For multi-concept erasure, our objective function offers a versatile plug-and-play solution that significantly boosts performance. Extensive experiments demonstrate that ANT achieves state-of-the-art results in both single and multi-concept erasure, delivering high-quality, safe outputs without compromising the generative fidelity. Code is available at https://github.com/lileyang1210/ANT
Code (2)
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) h…
Variational Composite Autoencoders
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward enc…
DecoderFeudal Steering: Hierarchical Learning for Steering Angle Prediction
We consider the challenge of automated steering angle prediction for self driving cars using egocentric road images. In this work, we explore the use of feudal networks, used in hierarchical reinforcement learning (HRL),…
Hierarchical Reinforcement LearningPredictionSelf-Driving CarsDenoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Linear Concept Vectors have proven effective for steering large language models (LLMs). While existing approaches like linear probing and difference-in-means derive these vectors from LLM hidden representations, diverse …
counterfactualDenoisingLanguage ModelingLanguage ModellingHow Diffusion Models Memorize
Despite their success in image generation, diffusion models can memorize training data, raising serious privacy and copyright concerns. Although prior work has sought to characterize, detect, and mitigate memorization, t…
Image Generation