Related papers: Reconstruction Attacks on Machine Unlearning: Simp…

The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a…

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model…

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…

Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memorization are generally unclear, particularly in scenarios where…

Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment. Despite this importance, existing approaches are often heuristic…

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a…

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…

Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In…

Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been…

Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or…

Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative approach, enabling…

Recently, an increasing number of laws have governed the useability of users' privacy. For example, Article 17 of the General Data Protection Regulation (GDPR), the right to be forgotten, requires machine learning applications to remove a…

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models. While training models have become more efficient and accurate, the importance of unlearning…

Machine Unlearning removes specific knowledge about training data samples from an already trained model. It has significant practical benefits, such as purging private, inaccurate, or outdated information from trained models without the…

Publicly releasing the specification of a model with its trained parameters means an adversary can attempt to reconstruct information about the training data via training data reconstruction attacks, a major vulnerability of modern machine…

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine…

Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more. Yet a…