• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

The security of latent dirichlet allocation (2015)

by Shike Mei, Xiaojin Zhu
Add To MetaCart

Tools

Sorted by:
Results 1 - 1 of 1

Some Submodular Data-Poisoning Attacks on Machine Learners

by Shike Mei, Xiaojin Zhu , 2015
"... We study data-poisoning attacks using a machine teaching framework. For a family of NP-hard attack problems we pose them as submodular function maximization, thereby inheriting efficient greedy algorithms with theoretical guarantees. We demonstrate some attacks with experiments. 1 ..."
Abstract - Add to MetaCart
We study data-poisoning attacks using a machine teaching framework. For a family of NP-hard attack problems we pose them as submodular function maximization, thereby inheriting efficient greedy algorithms with theoretical guarantees. We demonstrate some attacks with experiments. 1
(Show Context)

Citation Context

...attacks, we need to know first how the attacker may modify the training data to maximally manipulate the learned model while incurring minimal effort. Recently, we proposed a unified attack framework =-=[14, 15]-=- to compute the optimal data-poisoning attacks on machine learners. The framework accommodates a wide range of attack effectiveness measures, attacker effort measures, and victim machine learning algo...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University