Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval
Preprint
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Adversarial and Clean Data Are Not Twins2023
- Adversarial Examples for Hamming Space SearchIEEE Transactions on Cybernetics, 2018
- Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise ReductionIEEE Transactions on Dependable and Secure Computing, 2018
- Adversarial Examples in the Physical World2018
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks2018
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001