Some Submodular Data-Poisoning Attacks on Machine Learners
| dc.contributor.author | Mei, Shike | |
| dc.contributor.author | Zhu, Xiaojin | |
| dc.date.accessioned | 2017-03-08T18:56:17Z | |
| dc.date.available | 2017-03-08T18:56:17Z | |
| dc.date.issued | 2017-03-08T18:56:17Z | |
| dc.description.abstract | 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. | en |
| dc.identifier.citation | TR1822 | en |
| dc.identifier.other | TR1822 | |
| dc.identifier.uri | http://digital.library.wisc.edu/1793/76118 | |
| dc.language.iso | en_US | en |
| dc.relation.ispartofseries | tech reports;TR1822 | |
| dc.subject | Machine Teaching | en |
| dc.subject | Submodularity | en |
| dc.subject | Data Poisoning Attack | en |
| dc.title | Some Submodular Data-Poisoning Attacks on Machine Learners | en |
| dc.type | Technical Report | en |