Adaptive Generation of Unrestricted Adversarial Inputs

Authors: Isaac Dunn, Hadrien Pouget, Tom Melham, Daniel Kroening
Published: 2019-05-07 | Updated: 2019-10-01

Source: https://arxiv.org/abs/1905.02463

PDF: https://arxiv.org/pdf/1905.02463

AIにより推定されたラベル

敵対的サンプル 適応型敵対的訓練 敵対的攻撃検出

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some l_p norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted attacks, which are not constrained to a small and rather artificial subset of all possible adversarial inputs. We introduce a novel algorithm for generating such unrestricted adversarial inputs which, unlike prior work, is adaptive: it is able to tune its attacks to the classifier being targeted. It also offers a 400-2,000x speedup over the existing state of the art. We demonstrate our approach by generating unrestricted adversarial inputs that fool classifiers robust to perturbation-based attacks. We also show that, by virtue of being adaptive and unrestricted, our attack is able to defeat adversarial training against it.