The paper proposes Orthogonal Concept Erasure (OCE), a novel multiplicative parameter update method that achieves precise concept erasure in diffusion models while independently preserving overall gen…

The paper proposes Neighbor-Aware Localized Concept Erasure (NLCE), a training-free framework that effectively removes specific concepts from text-to-image models while minimizing the unintended degra…

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

The paper introduces TICoE, a text-image collaborative framework that achieves precise and faithful concept removal from text-to-image generative models, surpassing existing methods in both precision…

This paper systematically investigates unlearnable examples (UEs) across diverse training paradigms, finding that existing UEs fail under pretraining-finetuning (PF) settings, and proposes Shallow Sem…

The paper proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while main…

PURGE is a novel machine unlearning algorithm that leverages the duality between continual learning and unlearning to achieve high data retention while making the unlearned model indistinguishable fro…

This paper provides the first integrated analysis of model dememorization, unifying unlearnability and unlearning methods, and offering theoretical guarantees on dememorization depth.

The paper proposes AHV-D&S, a novel training-free inference-time safeguard that detects and suppresses risky content in Diffusion Transformers (DiTs) by quantifying token sensitivity across attention…

This paper proposes a modified SISA framework to achieve efficient class-level unlearning in CNNs, allowing the removal of specific data influence without full model retraining.

This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to…

The paper proposes Jellyfish, a zero-shot federated unlearning scheme that effectively removes the influence of forgotten data from federated learning models while maintaining model utility and privac…

The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.

SUPREME is an open-source, multi-GPU framework designed to efficiently and reproducibly evaluate machine unlearning methods for image classification by distributing computationally intensive tasks acr…

The paper introduces Asymmetric Langevin Unlearning (ALU), a novel framework that uses public data to significantly reduce the utility loss typically associated with certified machine unlearning, enab…

The paper proposes a novel, theoretically-grounded algorithm (HAMU) that addresses the challenge of machine unlearning by guaranteeing specified improvements in forget quality while minimizing retain…

Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…

AnchorSteer introduces a framework that achieves high-fidelity, structure-preserving music editing by decoupling semantic concept injection from structural constraints.

This paper introduces the first complete pipeline for federated unlearning, proposing an efficient unlearning approach and a novel visualization framework (Skyeye) to evaluate a model's forgetting cap…