相关论文: Inference-Time Machine Unlearning via Gated Activa…

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for…

Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to be forgotten} that mandates industry applications to remove…

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion…

Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introduces problems of its own. For example, in recurrent models…

While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks. Machine unlearning is pivotal for mitigating these risks, yet existing…

We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model…

Driven by privacy protection laws and regulations, unlearning in Large Language Models (LLMs) is gaining increasing attention. However, current research often neglects the interpretability of the unlearning process, particularly concerning…

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using methods such as LLM unlearning. However, unlearning a set of…

As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…

Machine unlearning is the process of removing the impact of a particular set of training samples from a pretrained model. It aims to fulfill the "right to be forgotten", which grants the individuals such as patients the right to reconsider…

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Class-level machine unlearning aims to remove the influence of specified classes while preserving model utility on retained classes. Existing methods are commonly evaluated by retain-set accuracy, forget-set accuracy, and unlearning time,…

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the…

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity…

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…