相关论文: Stake the Points: Structure-Faithful Instance Unle…

Machine learning models increasingly function as representational systems, yet the philosoph- ical assumptions underlying their internal structures remain largely unexamined. This paper develops a structuralist decision framework for…

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about the unauthorized use of copyrighted or sensitive data. Machine unlearning aims to remove such 'forget' data while preserving utility…

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove…

Machine unlearning is an emerging technology that has come to attract widespread attention. A number of factors, including regulations and laws, privacy, and usability concerns, have resulted in this need to allow a trained model to forget…

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…

Uncertainty estimation in machine learning has traditionally focused on the prediction stage, aiming to quantify confidence in model outputs while treating learned representations as deterministic and reliable by default. In this work, we…

Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses on single-task settings, whereas modern models often…

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted…

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearning (MU). However,…

Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge in this process is…

This paper addresses the current lack of a unified formal framework in machine learning theory, as well as the absence of robust theoretical foundations for interpretability and ethical safety assurance. We first construct a formal…

Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…

As Machine Learning (ML) evolves, the complexity and sophistication of security threats against this paradigm continue to grow as well, threatening data privacy and model integrity. In response, Machine Unlearning (MU) is a recent…

This work delves into the complexities of machine unlearning in the face of distributional shifts, particularly focusing on the challenges posed by non-uniform feature and label removal. With the advent of regulations like the GDPR…

Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on…

Machine Unlearning is an emerging field that addresses data privacy issues by enabling the removal of private or irrelevant data from the Machine Learning process. Challenges related to privacy and model efficiency arise from the use of…

Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been…

Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…