Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
Privacy-preserving instance encoding aims to encode raw data as feature vectors without revealing their privacy-sensitive information. When designed properly, these encodings can be used for downstream ML applications such as training and inference with limited privacy risk. However, the vast majority of existing instance encoding schemes are based on heuristics and their privacy-preserving properties are only validated empirically against a limited set of attacks. In this paper, we propose a theoretically-principled measure for the privacy of instance encoding based on Fisher information. We show that our privacy measure is intuitive, easily applicable, and can be used to bound the invertibility of encodings both theoretically and empirically.
Code (0)
등록된 구현이 없습니다.
Tasks
Privacy PreservingSimilar Papers 제목 키워드 기반
Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding
Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before sharing, with the hope that the encodin…
Is Private Learning Possible with Instance Encoding?
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algorithm can be made private by relying on an…
BIG-bench Machine LearningReconstruction Attack on Instance Encoding for Language Understanding
A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding. We propose a novel reconstruction attack to break TextHide by recoverin…
Privacy PreservingReconstruction AttackSentenceSentence ClassificationDifferentially Private Instance Encoding against Privacy Attacks
TextHide was recently proposed to protect the training data via instance encoding in natural language domain. Due to the lack of theoretic privacy guarantee, such instance encoding scheme has been shown to be vulnerable …
Reconstruction AttackDesign of Privacy-Preserving Dynamic Controllers
As a quantitative criterion for privacy of "mechanisms" in the form of data-generating processes, the concept of differential privacy was first proposed in computer science and has later been applied to linear dynamical …
Privacy Preserving