Special Issue "Black-Box Algorithms and Their Applications"

A special issue of Algorithms (ISSN 1999-4893).

Deadline for manuscript submissions: 1 November 2022 | Viewed by 779

Special Issue Editor

Dr. Huan Zhang
E-Mail Website
Guest Editor
Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Interests: machine learning; optimization; adversarial robustness; trustworthy artificial intelligence

Special Issue Information

Dear Colleagues,

Black-box algorithms require little to no information from the system under study and are often versatile and general enough to be applied to a wide range of problems in different domains. The most notable examples include black-box optimization algorithms such as zeroth-order and Bayesian optimization algorithms, which do not require derivatives or other explicit information for the function under optimization. Such algorithms have become an asset to various domains, such as machine learning, artificial intelligence, and cybersecurity. The scientific community can greatly benefit from the development of more efficient and scalable black-box algorithms.

We cordially invite you to submit high-quality research and review papers for this Special Issue on “Black-box Algorithms and Their Applications”, with subjects ranging from theories to applications of black-box algorithms. Submitted articles may focus on recent advances in black-box algorithms, including but not limited to:

  • The convergence, sample efficiency, acceleration, or other theoretical perspectives of black-box algorithms;
  • Novel applications of black-box algorithms, such as applications to machine learning, artificial intelligence, control theory, cybersecurity, and intelligent systems;
  • Software toolkits and benchmarks of black-box algorithms.

Dr. Huan Zhang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • black-box optimization
  • black-box function
  • zeroth order optimization
  • bayesian optimization
  • derivative-free optimization
  • stochastic approximation
  • black-box importance sampling
  • black-box robust optimization
  • black-box algorithms for machine learning
  • black-box algorithms for artificial intelligence
  • black-box algorithms for cybersecurity
  • black-box optimizers
  • black-box systems

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Simple Black-Box Universal Adversarial Attacks on Deep Neural Networks for Medical Image Classification
Algorithms 2022, 15(5), 144; https://doi.org/10.3390/a15050144 - 22 Apr 2022
Viewed by 500
Abstract
Universal adversarial attacks, which hinder most deep neural network (DNN) tasks using only a single perturbation called universal adversarial perturbation (UAP), are a realistic security threat to the practical application of a DNN for medical imaging. Given that computer-based systems are generally operated [...] Read more.
Universal adversarial attacks, which hinder most deep neural network (DNN) tasks using only a single perturbation called universal adversarial perturbation (UAP), are a realistic security threat to the practical application of a DNN for medical imaging. Given that computer-based systems are generally operated under a black-box condition in which only input queries are allowed and outputs are accessible, the impact of UAPs seems to be limited because well-used algorithms for generating UAPs are limited to white-box conditions in which adversaries can access model parameters. Nevertheless, we propose a method for generating UAPs using a simple hill-climbing search based only on DNN outputs to demonstrate that UAPs are easily generatable using a relatively small dataset under black-box conditions with representative DNN-based medical image classifications. Black-box UAPs can be used to conduct both nontargeted and targeted attacks. Overall, the black-box UAPs showed high attack success rates (40–90%). The vulnerability of the black-box UAPs was observed in several model architectures. The results indicate that adversaries can also generate UAPs through a simple procedure under the black-box condition to foil or control diagnostic medical imaging systems based on DNNs, and that UAPs are a more serious security threat. Full article
(This article belongs to the Special Issue Black-Box Algorithms and Their Applications)
Show Figures

Figure 1

Back to TopTop