Anonymization: The imperfect science of using data while preserving privacy

A Gadotti, L Rocher, F Houssiau, AM Creţu… - Science …, 2024 - science.org
Information about us, our actions, and our preferences is created at scale through surveys or
scientific studies or as a result of our interaction with digital devices such as smartphones …

Extracting training data from diffusion models

N Carlini, J Hayes, M Nasr, M Jagielski… - 32nd USENIX Security …, 2023 - usenix.org
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted
significant attention due to their ability to generate high-quality synthetic images. In this work …

Exploiting defenses against gan-based feature inference attacks in federated learning

X Luo, X Zhang - arxiv preprint arxiv:2004.12571, 2020 - arxiv.org
Federated learning (FL) is a decentralized model training framework that aims to merge
isolated data islands while maintaining data privacy. However, recent studies have revealed …

SoK: Let the privacy games begin! A unified treatment of data inference privacy in machine learning

A Salem, G Cherubin, D Evans, B Köpf… - … IEEE Symposium on …, 2023 - ieeexplore.ieee.org
Deploying machine learning models in production may allow adversaries to infer sensitive
information about training data. There is a vast literature analyzing different types of …

[HTML][HTML] Preserving data privacy in machine learning systems

SZ El Mestari, G Lenzini, H Demirci - Computers & Security, 2024 - Elsevier
The wide adoption of Machine Learning to solve a large set of real-life problems came with
the need to collect and process large volumes of data, some of which are considered …

" Get in Researchers; We're Measuring Reproducibility": A Reproducibility Study of Machine Learning Papers in Tier 1 Security Conferences

D Olszewski, A Lu, C Stillman, K Warren… - Proceedings of the …, 2023 - dl.acm.org
Reproducibility is crucial to the advancement of science; it strengthens confidence in
seemingly contradictory results and expands the boundaries of known discoveries …

Privacy inference attack and defense in centralized and federated learning: A comprehensive survey

B Rao, J Zhang, D Wu, C Zhu, X Sun… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The emergence of new machine learning methods has led to their widespread application
across various domains, significantly advancing the field of artificial intelligence. However …

Do SSL models have déjà vu? a case of unintended memorization in self-supervised learning

C Meehan, F Bordes, P Vincent… - Advances in Neural …, 2024 - proceedings.neurips.cc
Self-supervised learning (SSL) algorithms can produce useful image representations by
learning to associate different parts of natural images with one another. However, when …

Sok: Memorization in general-purpose large language models

V Hartmann, A Suri, V Bindschaedler, D Evans… - arxiv preprint arxiv …, 2023 - arxiv.org
Large Language Models (LLMs) are advancing at a remarkable pace, with myriad
applications under development. Unlike most earlier machine learning models, they are no …

Analyzing inference privacy risks through gradients in machine learning

Z Li, A Lowy, J Liu, T Koike-Akino, K Parsons… - Proceedings of the …, 2024 - dl.acm.org
In distributed learning settings, models are iteratively updated with shared gradients
computed from potentially sensitive user data. While previous work has studied various …