paper-with-me

홈 › Papers

Is Private Learning Possible with Instance Encoding?

2020-11-10 · Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramer

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.

📄 PDF Abstract BibTeX arXiv:2011.05315

Code (2)

Hazelsuko07/InstaHide_Challenge 공식 구현
xj231/FDN pytorch

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Reconstruction Attack on Instance Encoding for Language Understanding

2021-11-01 · EMNLP 2021 11 · Shangyu Xie, Yuan Hong

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 Classification

Differentially Private Instance Encoding against Privacy Attacks

2022-07-01 · NAACL (ACL) 2022 7 · Shangyu Xie, Yuan Hong

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 Attack

Learning to Select SAT Encodings for Pseudo-Boolean and Linear Integer Constraints

2023-07-18 · Felix Ulrich-Oltean, Peter Nightingale, James Alfred Walker

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

2019-07-09 · Jiahui Li, Zhiqiang Hu, Shuang Yang

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 SegmentationSegmentation

Learning Privacy Preserving Encodings through Adversarial Training

2018-02-14 · Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti

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