BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

2019 article gu2017badnets ○ Not yet verified

Authors

Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg

Venue

IEEE Access

Abstract

First demonstration of backdoor attacks on deep neural networks. Shows that small trigger patterns in training data cause models to misclassify any input containing the trigger (e.g., stop signs with stickers classified as speed limits).

BibTeX

Local Entry

@article{gu2017badnets,
  title = {BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain},
  author = {Tianyu Gu and Brendan Dolan-Gavitt and Siddharth Garg},
  year = {2019},
  journal = {IEEE Access},
  url = {https://arxiv.org/abs/1708.06733},
  abstract = {First demonstration of backdoor attacks on deep neural networks. Shows that small trigger patterns in training data cause models to misclassify any input containing the trigger (e.g., stop signs with stickers classified as speed limits).}
}

From OPENALEX

@article{gu2017badnets,
  title = {BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain},
  author = {Tianyu Gu and Brendan Dolan-Gavitt and Siddharth Garg},
  year = {2017},
  journal = {arXiv (Cornell University)},
  doi = {10.48550/arxiv.1708.06733}
}