Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$

Authors: Francesco Croce, Matthias Hein
Published: 2019-05-27 | Updated: 2020-04-24

Source: https://arxiv.org/abs/1905.11213

PDF: https://arxiv.org/pdf/1905.11213

AIにより推定されたラベル

評価手法 脆弱性管理 マルチクラス分類

※ 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

In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific l_p-perturbation models have been developed, we show that they do not come with any guarantee against other l_q-perturbations. We propose a new regularization scheme, MMR-Universal, for ReLU networks which enforces robustness wrt l₁– and l_∞-perturbations and show how that leads to the first provably robust models wrt any l_p-norm for p ≥ 1.