Universal Perturbation Attack Against Image Retrieval

@article{Li2019UniversalPA,
  title={Universal Perturbation Attack Against Image Retrieval},
  author={Jie Li and R. Ji and H. Liu and Xiaopeng Hong and Yue Gao and Q. Tian},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={4898-4907}
}
  • Jie Li, R. Ji, +3 authors Q. Tian
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has been paid to attacking image retrieval systems. In this paper, we make the first attempt in attacking image retrieval systems. Concretely, image retrieval attack is to make the retrieval system… Expand
Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower
AP-GAN: Adversarial patch attack on content-based image retrieval systems
Adversarial Attack and Defense in Deep Ranking
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing
Fooled by Imagination: Adversarial Attack to Image Captioning Via Perturbation in Complex Domain
Beyond Universal Person Re-Identification Attack
Universal Adversarial Perturbation Generated by Attacking Layer-wise Relevance Propagation
Universal Adversarial Perturbations: A Survey
...
1
2
3
4
...

References

SHOWING 1-10 OF 49 REFERENCES
Generalizable Data-Free Objective for Crafting Universal Adversarial Perturbations
Large-Scale Image Retrieval with Attentive Deep Local Features
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Mitigating adversarial effects through randomization
Generating Adversarial Examples with Adversarial Networks
Universal Adversarial Perturbations
Boosting Adversarial Attacks with Momentum
  • Y. Dong, Fangzhou Liao, +4 authors J. Li
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
Towards Evaluating the Robustness of Neural Networks
Aggregating Local Deep Features for Image Retrieval
...
1
2
3
4
5
...