Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks

Wei Jiang 0016, Xiangyu Wen, Jinyu Zhan, Xupeng Wang, Ziwei Song. Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks. IEEE Trans. on CAD of Integrated Circuits and Systems, 41(8):2611-2624, 2022. [doi]

@article{JiangWZWS22,
  title = {Interpretability-Guided Defense Against Backdoor Attacks to Deep Neural Networks},
  author = {Wei Jiang 0016 and Xiangyu Wen and Jinyu Zhan and Xupeng Wang and Ziwei Song},
  year = {2022},
  doi = {10.1109/TCAD.2021.3111123},
  url = {https://doi.org/10.1109/TCAD.2021.3111123},
  researchr = {https://researchr.org/publication/JiangWZWS22},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. on CAD of Integrated Circuits and Systems},
  volume = {41},
  number = {8},
  pages = {2611-2624},
}