paper-with-me

Papers

Algorithms that Remember: Model Inversion Attacks and Data Protection Law

2018-07-12 · Michael Veale, Reuben Binns, Lilian Edwards

Many individuals are concerned about the governance of machine learning systems and the prevention of algorithmic harms. The EU's recent General Data Protection Regulation (GDPR) has been seen as a core tool for achieving better governance of this area. While the GDPR does apply to the use of models in some limited situations, most of its provisions relate to the governance of personal data, while models have traditionally been seen as intellectual property. We present recent work from the information security literature around model inversion' and membership inference' attacks, which indicate that the process of turning training data into machine learned systems is not one-way, and demonstrate how this could lead some models to be legally classified as personal data. Taking this as a probing experiment, we explore the different rights and obligations this would trigger and their utility, and posit future directions for algorithmic governance and regulation.

📄 PDF Abstract BibTeX arXiv:1807.04644

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning

2023-05-31 · Junyi Zhu, Ruicong Yao, Matthew B. Blaschko

In Federated Learning (FL) and many other distributed training frameworks, collaborators can hold their private data locally and only share the network weights trained with the local data after multiple iterations. Gradi…

Federated Learning

A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning

2022-09-08 · Yan Kang, Jiahuan Luo, Yuanqin He, Xiaojin Zhang 외

Federated learning (FL) has emerged as a practical solution to tackle data silo issues without compromising user privacy. One of its variants, vertical federated learning (VFL), has recently gained increasing attention a…

Federated LearningPrivacy PreservingVertical Federated Learning

Dropout is NOT All You Need to Prevent Gradient Leakage

2022-08-12 · Daniel Scheliga, Patrick Mäder, Marco Seeland

Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they …

AllFederated Learningimage-classificationImage Classification

A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

2022-06-15 · Rui Zhang, Song Guo, Junxiao Wang, Xin Xie 외

Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and …

Survey

Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Study

2022-08-09 · Daniel Scheliga, Patrick Mäder, Marco Seeland

Gradient Inversion (GI) attacks are a ubiquitous threat in Federated Learning (FL) as they exploit gradient leakage to reconstruct supposedly private training data. Common defense mechanisms such as Differential Privacy …

Federated LearningImage ClassificationPrivacy Preserving