Anonymization: The imperfect science of using data while preserving privacy
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 …
scientific studies or as a result of our interaction with digital devices such as smartphones …
Extracting training data from diffusion models
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 …
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 …
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
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 …
information about training data. There is a vast literature analyzing different types of …
[HTML][HTML] Preserving data privacy in machine learning systems
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 …
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 …
seemingly contradictory results and expands the boundaries of known discoveries …
Privacy inference attack and defense in centralized and federated learning: A comprehensive survey
The emergence of new machine learning methods has led to their widespread application
across various domains, significantly advancing the field of artificial intelligence. However …
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
Self-supervised learning (SSL) algorithms can produce useful image representations by
learning to associate different parts of natural images with one another. However, when …
learning to associate different parts of natural images with one another. However, when …
Sok: Memorization in general-purpose large language models
Large Language Models (LLMs) are advancing at a remarkable pace, with myriad
applications under development. Unlike most earlier machine learning models, they are no …
applications under development. Unlike most earlier machine learning models, they are no …
Analyzing inference privacy risks through gradients in machine learning
In distributed learning settings, models are iteratively updated with shared gradients
computed from potentially sensitive user data. While previous work has studied various …
computed from potentially sensitive user data. While previous work has studied various …