.png){kind=icon}
Return
Algorithms that remember: model inversion attacks and data protection law
.png){kind=icon}
OA
AI
DOI：10.1098/rsta.2018.0083.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 indicates 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. This article is part of the theme issue 'Governing artificial intelligence: ethical, legal, and technical opportunities and challenges'.
Keywords:
model inversion
personal data
model trading
machine learning
Journal
P
IF:
3.7
Papers:
7.8K
Citations:
2.8W
Organization
Cited Papers
Mass-spectrometric characterization of cisplatin binding sites on native and denatured ubiquitin
PREAI
ShareSaveShareSaveSEMANTIC ANNOTATIONS ON HERITAGE MODELS: 2D/3D APPROACHES AND FUTURE RESEARCH CHALLENGES.png)
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesOAAI
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIF0
OAAIShareSaveShareSave
View more