Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval. (arXiv:2303.12658v1 [cs.CV])

Deep hashing has been extensively applied to massive image retrieval due to
its efficiency and effectiveness. Recently, several adversarial attacks have
been presented to reveal the vulnerability of deep hashing models against
adversarial examples. However, existing attack methods suffer from degraded
performance or inefficiency because they underutilize the semantic relations
between original samples or spend a lot of time learning these relations with a
deep neural network. In this paper, we propose a novel Pharos-guided Attack,
dubbed PgA, to evaluate …

adversarial adversarial attacks attack attacks efficiency evaluation hashing network neural network performance robustness vulnerability