Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world

no code implementations • 9 Mar 2020 • Ivan Fursov, Alexey Zaytsev, Nikita Kluchnikov, Andrey Kravchenko, Evgeny Burnaev

The first approach adopts a Monte-Carlo method and allows usage in any scenario, the second approach uses a continuous relaxation of models and target metrics, and thus allows usage of state-of-the-art methods for adversarial attacks with little additional effort.

Adversarial Attack