Related papers: SalUn: Empowering Machine Unlearning via Gradient-…

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…

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…

The need for effective unlearning mechanisms in large language models (LLMs) is increasingly urgent, driven by the necessity to adhere to data regulations and foster ethical generative AI practices. Despite growing interest of LLM…

Large language models (LLMs) require iterative updates to address the outdated information problem, where LLM unlearning offers an approach for selective removal. However, mainstream unlearning methods primarily rely on fine-tuning…

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Due to increasing privacy regulations and regulatory compliance, Machine Unlearning (MU) has become essential. The goal of unlearning is to remove information related to a specific class from a model. Traditional approaches achieve exact…

In machine unlearning, $(\varepsilon,\delta)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex…

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting…

Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge…

The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…

Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion…

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning (CU) emerges as an…

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from…

As Large Language Models (LLMs) increasingly shape online content, removing targeted information from well-trained LLMs (also known as LLM unlearning) has become critical for web governance. A key challenge lies in sample-wise imbalance…

Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between…

Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are proposed, which fine-tune MLLMs to reduce…

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

In current AI era, users may request AI companies to delete their data from the training dataset due to the privacy concerns. As a model owner, retraining a model will consume significant computational resources. Therefore, machine…