论文标题
智能应用程序攻击：在Android应用中攻击深度学习模型
Smart App Attack: Hacking Deep Learning Models in Android Apps
论文作者
论文摘要
设备深度学习在移动应用程序中迅速越来越受欢迎。与将深度学习从智能手机到云的卸载相比，在保留用户隐私的同时，在设备深度学习中可以推断离线模型。但是，这种机制不可避免地将模型存储在用户的智能手机上，并且可能会引起对抗性攻击，因为攻击者可以使用它们。由于设备模型的特征，大多数现有的对抗攻击不能直接用于设备模型。在本文中，我们通过基于确定的转移学习方法和Tensorflow Hub的预训练模型来制定高度相似的二进制分类模型，从而介绍了灰色框对面攻击框架，以侵入式模型。我们根据四种不同的设置，包括预训练的模型，数据集，转移学习方法和对抗性攻击算法来评估攻击效率和一般性。结果表明，不论不同的设置如何，拟议的攻击仍然有效，并且表现明显优于最先进的基线。我们进一步对从Google Play收集的现实世界深度学习移动应用程序进行了实证研究。在采用转移学习的53个应用程序中，我们发现其中71.7％可以成功攻击，其中包括具有关键用法场景的医学，自动化和金融类别中的流行。结果要求深入学习移动应用程序开发人员的意识和行动以确保设备模型。这项工作的代码可从https://github.com/jinxhy/smartappattack获得
On-device deep learning is rapidly gaining popularity in mobile applications. Compared to offloading deep learning from smartphones to the cloud, on-device deep learning enables offline model inference while preserving user privacy. However, such mechanisms inevitably store models on users' smartphones and may invite adversarial attacks as they are accessible to attackers. Due to the characteristic of the on-device model, most existing adversarial attacks cannot be directly applied for on-device models. In this paper, we introduce a grey-box adversarial attack framework to hack on-device models by crafting highly similar binary classification models based on identified transfer learning approaches and pre-trained models from TensorFlow Hub. We evaluate the attack effectiveness and generality in terms of four different settings including pre-trained models, datasets, transfer learning approaches and adversarial attack algorithms. The results demonstrate that the proposed attacks remain effective regardless of different settings, and significantly outperform state-of-the-art baselines. We further conduct an empirical study on real-world deep learning mobile apps collected from Google Play. Among 53 apps adopting transfer learning, we find that 71.7\% of them can be successfully attacked, which includes popular ones in medicine, automation, and finance categories with critical usage scenarios. The results call for the awareness and actions of deep learning mobile app developers to secure the on-device models. The code of this work is available at https://github.com/Jinxhy/SmartAppAttack
