Research Article
Unsupervised Multi-criteria Adversarial Detection in Deep Image Retrieval
@INPROCEEDINGS{10.1007/978-3-031-64948-6_8, author={Yanru Xiao and Cong Wang and Xing Gao}, title={Unsupervised Multi-criteria Adversarial Detection in Deep Image Retrieval}, proceedings={Security and Privacy in Communication Networks. 19th EAI International Conference, SecureComm 2023, Hong Kong, China, October 19-21, 2023, Proceedings, Part I}, proceedings_a={SECURECOMM}, year={2024}, month={10}, keywords={Deep hashing adversarial detection image retrieval}, doi={10.1007/978-3-031-64948-6_8} }- Yanru Xiao
Cong Wang
Xing Gao
Year: 2024
Unsupervised Multi-criteria Adversarial Detection in Deep Image Retrieval
SECURECOMM
Springer
DOI: 10.1007/978-3-031-64948-6_8
Abstract
The vulnerability in the algorithm supply chain of deep learning has imposed new challenges to image retrieval systems in the downstream. Among a variety of techniques, deep hashing is gaining popularity. As it inherits the algorithmic backend from deep learning, a handful of attacks are recently proposed to disrupt normal image retrieval. Unfortunately, the defense strategies in softmax classification are not readily available to be applied in the image retrieval domain. In this paper, we propose an efficient and unsupervised scheme to identify unique adversarial behaviors in the hamming space. In particular, we design three criteria from the perspectives of hamming distance, quantization loss and denoising to defend against both untargeted and targeted attacks, which collectively limit the adversarial space. The extensive experiments on four datasets demonstrate 2–23% improvements of detection rates with minimum computational overhead for real-time image queries.
