Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.9
2.1
Journals
Entropy
Special Issues
Information-Theoretic Methods for Trustworthy Machine Learning
entropy-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Entropy Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Information-Theoretic Methods for Trustworthy Machine Learning

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".

Deadline for manuscript submissions: 31 October 2025 | Viewed by 1199

Special Issue Editors

Dr. Sanghamitra Dutta

E-Mail Website
Guest Editor
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
Interests: trustworthy machine learning; fairness and explainability; information theory; optimization; statistics; estimation theory; causal inference; coded computing
Prof. Dr. Syed A. Jafar

grade E-Mail Website
Guest Editor
Electrical Engineering and Computer Science, University of California Irvine, Irvine, CA 92697-2625, USA
Interests: capacity of wireless networks; private/secure/coded/distributed storage/retrieval/computation; network coding; network information theory; quantum information theory
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning has advanced significantly in recent years, fundamentally revolutionizing decision-making in several applications. While these models excel at learning all patterns embedded in the data, blindly learning all patterns can have unintended consequences, raising concerns regarding security, privacy, fairness, explainability, robustness, and reliability. Thus, the following question must be answered: How can we design machine learning models responsibly to ensure trustworthy decision making?

Information-theoretic methods play a pivotal role in ensuring the trustworthiness of machine learning systems via the rigorous quantification and analysis of fundamental limits. Information-theoretic methods are useful in analyzing the flow of information within machine learning pipelines, identifying vulnerabilities and potential biases, developing strategies for privacy and security, and ensuring robustness under unreliability and adversaries. In essence, information-theoretic methods contribute to building machine learning systems that are transparent, accountable, and dependable, thereby fostering trust among users and stakeholders.

The Special Issue welcomes the submission of previously unpublished papers on information-theoretic methods for trustworthy machine learning. The scope of this Special Issue includes, but is not limited to, fairness, explainability, security, privacy, reliability, and robustness.

Dr. Sanghamitra Dutta
Prof. Dr. Syed A. Jafar
Guest Editors

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. Entropy 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 2600 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

  • fairness
  • explainability
  • reliability
  • privacy
  • security
  • robustness

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 1923 KiB  
Article
PRG4CNN: A Probabilistic Model Checking-Driven Robustness Guarantee Framework for CNNs
by Yang Liu and Aohui Fang
Entropy 2025, 27(2), 163; https://doi.org/10.3390/e27020163 - 3 Feb 2025
Viewed by 756
Abstract
As an important kind of DNN (deep neural network), CNN (convolutional neural network) has made remarkable progress and been widely used in the vision and decision-making of autonomous robots. Nonetheless, in many scenarios, even a minor perturbation in input for CNNs may lead [...] Read more.
As an important kind of DNN (deep neural network), CNN (convolutional neural network) has made remarkable progress and been widely used in the vision and decision-making of autonomous robots. Nonetheless, in many scenarios, even a minor perturbation in input for CNNs may lead to serious errors, which means CNNs lack robustness. Formal verification is an effective method to guarantee the robustness of CNNs. Existing works predominantly concentrate on local robustness verification, which requires considerable time and space. Probabilistic robustness quantifies the robustness of CNNs, which is a practical mode of potential measurement. The state-of-the-art of probabilistic robustness verification is a test-driven approach, which is used to manually decide whether a DNN satisfies the probabilistic robustness and does not involve robustness repair. Robustness repair can improve the robustness of CNNs further. To address this issue, we propose a probabilistic model checking-driven robustness guarantee framework for CNNs, i.e., PRG4CNN. This is the first automated and complete framework for guaranteeing the probabilistic robustness of CNNs. It comprises four steps, as follows: (1) modeling a CNN as an MDP (Markov decision processes) by model learning, (2) specifying the probabilistic robustness of the CNN via the PCTL (Probabilistic Computational Tree Logic) formula, (3) verifying the probabilistic robustness with a probabilistic model checker, and (4) probabilistic robustness repair by counterexample-guided sensitivity analysis, if probabilistic robustness does not hold on the CNN. We here conduct experiments on various scales of CNNs trained on the handwriting dataset MNIST, and demonstrate the effectiveness of PRG4CNN. Full article
(This article belongs to the Special Issue Information-Theoretic Methods for Trustworthy Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop