You See What I Want You to See: Exploring Targeted Black-Box Transferability Attack for Hash-based Image Retrieval Systems
You See What I Want You to See: Exploring Targeted Black-Box Transferability Attack for Hash-based Image Retrieval Systems
复制标题
DOI：
10.1109/cvpr46437.2021.00197
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Yanru Xiao;Cong Wang
中科院分区：
文献类型：
--
作者：
Yanru Xiao;Cong Wang
随着大量的多媒体内容在线，深度哈希已经成为一种流行的方法，有效的图像检索和存储。然而，通过继承softmax分类的算法后端，这些技术也容易受到众所周知的对抗性示例的影响。将大量在线图像收集到数据库中也开辟了新的攻击途径。攻击者可以将对抗图像嵌入数据库，并针对用户查询检索的特定类别。在本文中，我们从对抗的角度出发，探索和增强深度哈希的目标黑盒可转移性攻击的能力。我们通过一系列的实证研究来激励这项工作，以了解图像检索中的独特挑战。利用随机噪声作为代理，研究了对抗子空间与黑盒可转移性之间的关系。然后，我们开发了一种新的攻击，同时是对抗性和鲁棒性的噪声，以提高可转移性。我们的实验结果表明，约1.2-3倍的黑盒可转移性相比，国家的最先进的机制。该代码可从以下网址获得：https://github.com/SugarRuy/CVPR21_Transferred_Hash。
With the large multimedia content online, deep hashing has become a popular method for efficient image retrieval and storage. However, by inheriting the algorithmic back-end from softmax classification, these techniques are vulnerable to the well-known adversarial examples as well. The massive collection of online images into the database also opens up new attack vectors. Attackers can embed adversarial images into the database and target specific categories to be retrieved by user queries. In this paper, we start from an adversarial standpoint to explore and enhance the capacity of targeted black-box transferability attack for deep hashing. We motivate this work by a series of empirical studies to see the unique challenges in image retrieval. We study the relations between adversarial subspace and black-box transferability via utilizing random noise as a proxy. Then we develop a new attack that is simultaneously adversarial and robust to noise to enhance transferability. Our experimental results demonstrate about 1.2-3× improvements of black-box transferability compared with the state-of-the-art mechanisms. The code is available at: https://github.com/SugarRuy/CVPR21_Transferred_Hash.