Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
Zhao, Pu, Chen, Pin-Yu, Wang, Siyue, Lin, Xue
Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability. Various adversarial attacks are proposed to sabotage the learning performance of DNN models. Among those, the black-box adversarial attack methods have received special attentions owing to their practicality and simplicity. Black-box attacks usually prefer less queries in order to maintain stealthy and low costs. However, most of the current black-box attack methods adopt the first-order gradient descent method, which may come with certain deficiencies such as relatively slow convergence and high sensitivity to hyper-parameter settings. In this paper, we propose a zeroth-order natural gradient descent (ZO-NGD) method to design the adversarial attacks, which incorporates the zeroth-order gradient estimation technique catering to the black-box attack scenario and the second-order natural gradient descent to achieve higher query efficiency. The empirical evaluations on image classification datasets demonstrate that ZO-NGD can obtain significantly lower model query complexities compared with state-of-the-art attack methods.
Feb-18-2020
- Country:
- North America
- United States
- Massachusetts > Suffolk County
- Boston (0.04)
- Indiana > Hamilton County
- Fishers (0.04)
- Massachusetts > Suffolk County
- Canada > Ontario
- Toronto (0.14)
- United States
- Europe > France
- Hauts-de-France > Nord > Lille (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America
- Genre:
- Research Report (1.00)
- Industry:
- Transportation > Air (1.00)
- Information Technology > Security & Privacy (1.00)
- Government (1.00)
- Technology: