Related papers: Amnesiac Machine Learning
Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted…
Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may…
With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand from a machine learning (ML) model. In the last few years, there have been notable developments in machine…
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…
We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten."…
Graph unlearning methods aim to efficiently remove the impact of sensitive data from trained GNNs without full retraining, assuming that deleted information cannot be recovered. In this work, we challenge this assumption by introducing the…
Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…
Data augmentation is widely used to mitigate data bias in the training dataset. However, data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. In this paper, we propose an effective…
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…
Privacy regulations require the erasure of data from deep learning models. This is a significant challenge that is amplified in Federated Learning, where data remains on clients, making full retraining or coordinated updates often…
Machine learning and data systems increasingly function as infrastructures of memory: they ingest, store, and operationalize traces of personal, political, and cultural life. Yet contemporary governance demands credible forms of forgetting,…
As the prevalence of data-driven technologies in healthcare continues to rise, concerns regarding data privacy and security become increasingly paramount. This thesis aims to address the vulnerability of personalized healthcare models,…
Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…
We study the right to be forgotten (GDPR Art. 17) for large language models and frame unlearning as a reproducible systems problem. Our approach treats training as a deterministic program and logs a minimal per-microbatch record (ordered ID…
The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology companies…
As a means to balance the growth of the AI industry with the need for privacy protection, machine unlearning plays a crucial role in realizing the ``right to be forgotten'' in artificial intelligence. This technique enables AI systems to…
Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…
Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearning (FU) has emerged to address the "right to be forgotten" and to remove the influence of…
The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…