• DOI:10.1145/3270101.3270106
Corpus ID: 52182712

Towards Query Efficient Black-box Attacks: An Input-free Perspective

@article{Du2018TowardsQE,
  title={Towards Query Efficient Black-box Attacks: An Input-free Perspective},
  author={Yali Du and Meng Fang and Jinfeng Yi and J. Cheng and D. Tao},
  journal={Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security},
  year={2018}
}

• Yali Du, Meng Fang, +2 authors D. Tao
• Published 2018
• Computer Science, Mathematics
• Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. [...] Key Method Following this approach, we propose two techniques to significantly reduce the query complexity. First, we initialize an adversarial example with a gray color image on which every pixel has roughly the same importance for the target model. Then we shrink the dimension of the attack space by perturbing a small region and tiling it to cover the input image.Expand

View on ACM

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed