Detecting adversarial examples with inductive Venn-ABERS predictors
the european symposium on artificial neural networks(2019)
Abstract
Inductive Venn-ABERS predictors (IVAPs) are a type of probabilistic predictors with the theoretical guarantee that their predictions are perfectly calibrated. We propose to exploit this calibration property for the detection of adversarial examples in binary classification tasks. By rejecting predictions if the uncertainty of the IVAP is too high, we obtain an algorithm that is both accurate on the original test set and significantly more robust to adversarial examples. The method appears to be competitive to the state of the art in adversarial defense, both in terms of robustness as well as scalability
MoreTranslated text
Key words
adversarial examples,predictors,venn-abers
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined