Related papers: SUA: Stealthy Multimodal Large Language Model Unle…

LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized…

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…

Machine unlearning allows data owners to erase the impact of their specified data from trained models. Unfortunately, recent studies have shown that adversaries can recover the erased data, posing serious threats to user privacy. An…

Machine Unlearning (MU) has recently gained considerable attention due to its potential to achieve Safe AI by removing the influence of specific data from trained Machine Learning (ML) models. This process, known as knowledge removal,…

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…

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds…

Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLMs generate text by…

The widespread adoption of large language models (LLMs) has raised concerns regarding data privacy. This study aims to investigate the potential for privacy invasion through input reconstruction attacks, in which a malicious model provider…

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification…

Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typically formulate forgetting and retention as a regularized…

Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowledge of LLMs. Tool-augmented LLMs need the ability to forget…

Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily reversed. To address…

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to…

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

Although Multimodal Large Language Models (MLLMs) have achieved remarkable progress across many domains, their training on large-scale multimodal datasets raises serious privacy concerns, making effective machine unlearning increasingly…

We propose Sensitivity-Uncertainty Alignment (SUA), a framework for analyzing failures of large language models under adversarial and ambiguous inputs. We argue that adversarial sensitivity and ambiguity reflect a common issue: misalignment…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such…

While recent research increasingly showcases the remarkable capabilities of Large Language Models (LLMs), it is equally crucial to examine their associated risks. Among these, privacy and security vulnerabilities are particularly…