Related papers: Erase or Hide? Suppressing Spurious Unlearning Neu…
Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficiency and robustness, offering an attractive alternative to…
Neural networks unintentionally memorize training data, creating privacy risks in federated learning (FL) systems, such as inference and reconstruction attacks on sensitive data. To mitigate these risks and to comply with privacy…
Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowledge, this ``forgotten" information remains precariously…
Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based…
"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often…
Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as…
We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be…
Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…
Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…
Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is…
Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for selective removal. While machine unlearning offers a principled…
Recently, the practical needs of ``the right to be forgotten'' in federated learning gave birth to a paradigm known as federated unlearning, which enables the server to forget personal data upon the client's removal request. Existing…
Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted the need for erasing datapoints from diffusion models.…
Machine Unlearning (MU) aims to selectively erase the influence of specific data points from pretrained models. However, most existing MU methods rely on the retain set to preserve model utility, which is often impractical due to privacy…
With growing concerns surrounding privacy and regulatory compliance, the concept of machine unlearning has gained prominence, aiming to selectively forget or erase specific learned information from a trained model. In response to this…
While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…
This paper explores Machine Unlearning (MU), an emerging field that is gaining increased attention due to concerns about neural models unintentionally remembering personal or sensitive information. We present SeUL, a novel method that…
The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…
Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU learning is to sample a set of pseudo-negatives from the…
Machine unlearning for security is studied in this context. Several spam email detection methods exist, each of which employs a different algorithm to detect undesired spam emails. But these models are vulnerable to attacks. Many attackers…