Related papers: Decoupling the Class Label and the Target Concept …
As machine learning systems increasingly rely on data subject to privacy regulation, selectively unlearning specific information from trained models has become essential. In image classification, this involves removing the influence of…
Machine unlearning is a fundamental mechanism that enforces the right to be forgotten. Existing unlearning studies that rely on label manipulation or task-gradient reversal often deliver limited unlearning effectiveness. Moreover, they can…
Machine unlearning is a process to remove specific data points from a trained model while maintaining the performance on the retain data, addressing privacy or legal requirements. Despite its importance, existing unlearning evaluations tend…
Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they often inherit harmful or unwanted knowledge from noisy…
Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization…
Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning literature for generative models is rather limited. The…
Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches have been proposed to solve this problem, they only utilize…
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…
Machine unlearning, which enables a model to forget specific data upon request, is increasingly relevant in the era of privacy-centric machine learning, particularly within federated learning (FL) environments. This paper presents a…
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations like the ``right to be…
Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing…
In Machine Learning, the emergence of \textit{the right to be forgotten} gave birth to a paradigm named \textit{machine unlearning}, which enables data holders to proactively erase their data from a trained model. Existing machine…
Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates…
A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…
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…
Data unlearning aims to remove the influence of specific training samples from a trained model without requiring full retraining. Unlike concept unlearning, data unlearning in diffusion models remains underexplored and often suffers from…
The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge…
The demand for data privacy has led to the development of frameworks like Federated Graph Learning (FGL), which facilitate decentralized model training. However, a significant operational challenge in such systems is adhering to the right…
Machine unlearning addresses the problem of updating a machine learning model/system trained on a dataset $S$ so that the influence of a set of deletion requests $U \subseteq S$ on the unlearned model is minimized. The gold standard…