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 instance-encoding mechanism that modifies the training inputs before feeding them to a normal learner. We formalize both the notion of instance encoding and its privacy by providing two attack models. We first prove impossibility results for achieving a (stronger) model. Next, we demonstrate practical attacks in the second (weaker) attack model on InstaHide, a recent proposal by Huang, Song, Li and Arora [ICML'20] that aims to use instance encoding for privacy.
Code (2)
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Reconstruction 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 AttackLearning to Select SAT Encodings for Pseudo-Boolean and Linear Integer Constraints
Many constraint satisfaction and optimisation problems can be solved effectively by encoding them as instances of the Boolean Satisfiability problem (SAT). However, even the simplest types of constraints have many encodi…
Accurate Nuclear Segmentation with Center Vector Encoding
Nuclear segmentation is important and frequently demanded for pathology image analysis, yet is also challenging due to nuclear crowdedness and possible occlusion. In this paper, we present a novel bottom-up method for nu…
Nuclear SegmentationSegmentationLearning Privacy Preserving Encodings through Adversarial Training
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fi…
AttributePrivacy Preserving