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

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…

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…

The paper proposes a novel bi-level exact unlearning attack targeting Large Reasoning Models (LRMs) that forces incorrect final answers while generating misleading reasoning traces, highlighting new s…

This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPE…

The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection a…

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper introduces Involuntary In-Context Learning (IICL), an effective few-shot pattern completion attack that can bypass safety alignments in large language models, achieving a 24.0% bypass rate a…

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

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 introduces 'unlearning corruption attacks,' demonstrating that the performance degradation inherent in approximate graph unlearning can be exploited by an adversary to significantly reduce…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performa…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embeddin…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…