Related papers: Make Text Unlearnable: Exploiting Effective Patter…

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…

We formulate the machine unlearning problem as a general constrained optimization problem. It unifies the first-order methods from the approximate machine unlearning literature. This paper then introduces the concept of feasible updates as…

The extraction of relevant data from Electronic Health Records (EHRs) is crucial to identifying symptoms and automating epidemiological surveillance processes. By harnessing the vast amount of unstructured text in EHRs, we can detect…

In an era of widespread web scraping, unlearnable dataset methods have the potential to protect data privacy by preventing deep neural networks from generalizing. But in addition to a number of practical limitations that make their use…

Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure of data utilization for model learning by adding…

Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studies have begun to tackle the privacy concerns associated with this data collection method.…

Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original image, thereby making…

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…

Learning an explainable classifier often results in low accuracy model or ends up with a huge rule set, while learning a deep model is usually more capable of handling noisy data at scale, but with the cost of hard to explain the result and…

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…

High-quality data plays an indispensable role in the era of large models, but the use of unauthorized data for model training greatly damages the interests of data owners. To overcome this threat, several unlearnable methods have been…

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms…

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable…

The unauthorized use of personal data in model training has emerged as a growing privacy threat. Unlearnable examples (UEs) address this issue by embedding imperceptible perturbations into benign examples to obstruct feature learning.…

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as…

Machine Unlearning aims to remove specific data from trained models, addressing growing privacy and ethical concerns. We provide a theoretical analysis of a simple and widely used method - gradient ascent - used to reverse the influence of…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…