The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Kevin Roth · Yannic Kilcher · Thomas Hofmann

Wed Jun 12th 11:20 -- 11:25 AM @ Grand Ballroom

We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack. These statistics can be easily computed and calibrated by randomly corrupting inputs. They exploit certain anomalies that adversarial attacks introduce, in particular if they follow the paradigm of choosing perturbations optimally under p-norm constraints. Access to the log-odds is the only requirement to defend models. We justify our approach empirically, but also provide conditions under which detectability via the suggested test statistics is guaranteed to be effective. In our experiments, we show that it is even possible to correct test time predictions for adversarial attacks with high accuracy.

Author Information

Kevin Roth (ETH Zurich)
Yannic Kilcher (ETH Zurich)
Thomas Hofmann (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors