2023/04/09 by Yanru Xiao, Cong Wang, Xiao, Yanru +3 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Adversarial Robustness in Machine Learning #Adversarial system #Algorithm #Artificial intelligence #Block code #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Decoding methods #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Hamming code #Hamming distance #Hamming space #Hash function #Image (mathematics) #Image retrieval #Information Retrieval (cs.IR) #Machine learning #Pattern recognition (psychology)
paper · pdf · doi:10.48550/arxiv.2304.04228
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/04/09 · openalex created_date 2023/04/12 · openalex updated_date 2026/07/28
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.