mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural Networks

Authors: Hai Shu, Ronghua Shi, Qiran Jia, Hongtu Zhu, Ziqi Chen
Published: 2020-06-05 | Updated: 2022-05-08

Source: https://arxiv.org/abs/2006.03243

PDF: https://arxiv.org/pdf/2006.03243

AIにより推定されたラベル

敵対的攻撃検出 攻撃タイプ アルゴリズム

※ 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

Deep neural networks (DNNs) have achieved great success in image classification, but can be very vulnerable to adversarial attacks with small perturbations to images. To improve adversarial image generation for DNNs, we develop a novel method, called mFI-PSO, which utilizes a Manifold-based First-order Influence measure for vulnerable image and pixel selection and the Particle Swarm Optimization for various objective functions. Our mFI-PSO can thus effectively design adversarial images with flexible, customized options on the number of perturbed pixels, the misclassification probability, and the targeted incorrect class. Experiments demonstrate the flexibility and effectiveness of our mFI-PSO in adversarial attacks and its appealing advantages over some popular methods.