Advbox: a toolbox to generate adversarial examples that fool neural networks

Authors: Dou Goodman, Hao Xin, Wang Yang, Wu Yuesheng, Xiong Junfeng, Zhang Huan
Published: 2020-01-13 | Updated: 2020-08-26

Source: https://arxiv.org/abs/2001.05574

PDF: https://arxiv.org/pdf/2001.05574

AIにより推定されたラベル

敵対的攻撃手法 敵対的サンプル ポイズニング

※ 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, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images are sufficient to fool the most powerful neural networks. Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle, PyTorch, Caffe2, MxNet, Keras, TensorFlow and it can benchmark the robustness of machine learning models. Compared to previous work, our platform supports black box attacks on Machine-Learning-as-a-service, as well as more attack scenarios, such as Face Recognition Attack, Stealth T-shirt, and DeepFake Face Detect. The code is licensed under the Apache 2.0 and is openly available at https://github.com/advboxes/AdvBox. Advbox now supports Python 3.