相关论文: Statistical Roughness-Informed Machine Unlearning

With the rapid advancement of AI applications, the growing needs for data privacy and model robustness have highlighted the importance of machine unlearning, especially in thriving graph-based scenarios. However, most existing graph…

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies…

When training a machine learning model with observational data, it is often encountered that some values are systemically missing. Learning from the incomplete data in which the missingness depends on some covariates may lead to biased…

As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting,…

Although deep learning (DL) has gained much popularity for accelerated magnetic resonance imaging (MRI), recent studies have shown that DL-based MRI reconstruction models could be oversensitive to tiny input perturbations (that are called…

The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable…

Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…

Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and…

Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively…

Machine unlearning poses challenges in removing mislabeled, contaminated, or problematic data from a pretrained model. Current unlearning approaches and evaluation metrics are solely focused on model predictions, which limits insight into…

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradation on retaining…

Federated Unlearning (FU) is emerging as a powerful tool that enables the selective removal of client data to effectively address data contamination and meet strict privacy regulations in mobile edge computing (MEC) systems. Although FU has…

With growing emphasis on privacy regulations, machine unlearning has become increasingly critical in real-world applications such as social networks and recommender systems, many of which are naturally represented as graphs. However,…

Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency. Stochastic variance-reduced gradient methods such as SVRG have been applied to…

As the popularity of deep learning (DL) in the field of magnetic resonance imaging (MRI) continues to rise, recent research has indicated that DL-based MRI reconstruction models might be excessively sensitive to minor input disturbances,…

Graph Machine Learning is essential for understanding and analyzing relational data. However, privacy-sensitive applications demand the ability to efficiently remove sensitive information from trained graph neural networks (GNNs), avoiding…

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…

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Modern recommender systems face a critical challenge in complying with privacy regulations like the 'right to be forgotten': removing a user's data without disrupting recommendations for others. Traditional unlearning methods address this…

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…