Some Submodular Data-Poisoning Attacks on Machine Learners

dc.contributor.authorMei, Shike
dc.contributor.authorZhu, Xiaojin
dc.date.accessioned2017-03-08T18:56:17Z
dc.date.available2017-03-08T18:56:17Z
dc.date.issued2017-03-08T18:56:17Z
dc.description.abstractWe 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.en
dc.identifier.citationTR1822en
dc.identifier.otherTR1822
dc.identifier.urihttp://digital.library.wisc.edu/1793/76118
dc.language.isoen_USen
dc.relation.ispartofseriestech reports;TR1822
dc.subjectMachine Teachingen
dc.subjectSubmodularityen
dc.subjectData Poisoning Attacken
dc.titleSome Submodular Data-Poisoning Attacks on Machine Learnersen
dc.typeTechnical Reporten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
TR1822.pdf
Size:
530.98 KB
Format:
Adobe Portable Document Format
Description:
tech report

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
2.03 KB
Format:
Item-specific license agreed upon to submission
Description: