ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
Diffusion models excel at generating high-quality, diverse images but suffer from training data memorization, raising critical privacy and safety concerns. Data unlearning has emerged to mitigate this issue by removing the influence of specific data without retraining from scratch. We propose ReTrack, a fast and effective data unlearning method for diffusion models. ReTrack employs importance sampling to construct a more efficient fine-tuning loss, which we approximate by retaining only dominant terms. This yields an interpretable objective that redirects denoising trajectories toward the $k$-nearest neighbors, enabling efficient unlearning while preserving generative quality. Experiments on MNIST T-Shirt, CelebA-HQ, CIFAR-10, and Stable Diffusion show that ReTrack achieves state-of-the-art performance, striking the best trade-off between unlearning strength and generation quality preservation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Investigating Model Editing for Unlearning in Large Language Models
Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performan…
PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
We introduce PoreTrack3D, the first benchmark for dynamic 3D Gaussian splatting in pore-scale, non-rigid 3D facial trajectory tracking. It contains over 440,000 facial trajectories in total, among which more than 52,000 …
3D ReconstructionLUNAR: LLM Unlearning via Neural Activation Redirection
Large Language Models (LLMs) benefit from training on ever larger amounts of textual data, but as a result, they increasingly incur the risk of leaking private information. The ability to selectively remove knowledge fro…
Replay What Matters: Off-Policy Replay for Efficient LLM Reinforcement Unlearning
LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unl…
ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering
We present Retriever-Transducer-Checker (ReTraCk), a neural semantic parsing framework for large scale knowledge base question answering (KBQA). ReTraCk is designed as a modular framework to maintain high flexibility. It…
Knowledge Base Question AnsweringQuestion AnsweringSemantic Parsing