An empirical study of derivative-free-optimization algorithms for targeted black-box attacks in deep neural networks

DOI10.1007/s11081-021-09652-wzbMath1498.90252arXiv2012.01901OpenAlexW3175732721MaRDI QIDQ2168625

Giuseppe Ughi, Jared Tanner, Vinayak Abrol

Publication date: 26 August 2022

Published in: Optimization and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.01901

zbMATH Keywords

derivative free optimizationdeep learningblack-box attacks

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Derivative-free methods and methods using generalized derivatives (90C56)

Related Items (1)

Surrogate-based branch-and-bound algorithms for simulation-based black-box optimization

Cites Work

• Unnamed Item
• Self-Correcting Geometry in Model-Based Algorithms for Derivative-Free Unconstrained Optimization
• Recursive Trust-Region Methods for Multiscale Nonlinear Optimization
• Introduction to Derivative-Free Optimization
• Improving the Flexibility and Robustness of Model-based Derivative-free Optimization Solvers
• Benchmarking Derivative-Free Optimization Algorithms
• Derivative-free optimization methods

This page was built for publication: An empirical study of derivative-free-optimization algorithms for targeted black-box attacks in deep neural networks