"Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference ..."

Zhen Xiang, David J. Miller, George Kesidis (2019)

> Home

Details and statistics

DOI: —

access: open

type: Informal or Other Publication

metadata version: 2019-08-30

- view
  - electronic edition @ arxiv.org (open access)
- export record
  dblp key:
  - journals/corr/abs-1908-10498
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-1908-10498
Zhen Xiang, David J. Miller, George Kesidis:
Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification. CoRR abs/1908.10498 (2019)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.