Controllable and Reliable AI

A special issue of AI (ISSN 2673-2688). This special issue belongs to the section "AI Systems: Theory and Applications".

Deadline for manuscript submissions: 31 May 2026 | Viewed by 747

Special Issue Editors


E-Mail Website
Guest Editor
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, 10 Xitucheng Rd, Beijing 100876, China
Interests: generative Al; multimodal computing; visual perception; intelligent medicine; edge computing and big data; large language model

E-Mail Website
Guest Editor
School of Computer Science, Beijing University of Posts and Telecommunications, 10 Xitucheng Rd., Beijing 100876, China
Interests: light field display generation; real-time 3D reconstruction technology; light field encoding and efficient transmission; end-cloud collaborative rendering technology; 3D digital human modeling and intelligent drive

E-Mail
Guest Editor
APEC Study Center of Nankai University, Nanjing, China
Interests: artificial intelligence

Special Issue Information

Dear Colleagues,

We are pleased to invite you to contribute to this Special Issue of AI, entitled “Controllable and Reliable AI”. As artificial intelligence (AI) systems increasingly permeate critical domains—from healthcare and autonomous systems to finance and public policy—ensuring their controllability and reliability has become a paramount concern. This Special Issue seeks to advance the discourse on developing AI technologies that are not only high-performing but also transparent, accountable, and aligned with human values. We invite cutting-edge research addressing theoretical frameworks, methodological innovations, and practical implementations that enhance the safety, robustness, and ethical governance of AI systems.

In this Special Issue, both original research articles and reviews are welcome. Topics may include (but are not limited to) controllability, reliability, and general AI.

The following is a list of relevant topics:

  • Computer vision;
  • Edge computing;
  • Foundation models;
  • Integrated sensing and communication;
  • Internet of things;
  • Ethics and policy.

Dr. Li Xiao
Dr. Yongping Xiong
Dr. Jingjia Zhang
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. AI 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 1600 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

  • computer vision
  • edge computing
  • foundation models
  • integrated sensing and communication
  • internet of things
  • ethics and policy

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (1 paper)

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

Research

17 pages, 8746 KiB  
Article
Scrub-and-Learn: Category-Aware Weight Modification for Machine Unlearning
by Jiali Wang, Hongxia Bie, Zhao Jing and Yichen Zhi
AI 2025, 6(6), 108; https://doi.org/10.3390/ai6060108 - 22 May 2025
Viewed by 376
Abstract
(1) Background: Machine unlearning plays a crucial role in privacy protection and model optimization, particularly in forgetting entire categories of data in classification tasks. However, existing methods often struggle with high computational costs, such as estimating the inverse Hessian, or require access to [...] Read more.
(1) Background: Machine unlearning plays a crucial role in privacy protection and model optimization, particularly in forgetting entire categories of data in classification tasks. However, existing methods often struggle with high computational costs, such as estimating the inverse Hessian, or require access to the original training data, limiting their practicality. (2) Methods: In this work, we introduce Scrub-and-Learn, which is a category-aware weight modification framework designed to remove class-level knowledge efficiently. By modeling unlearning as a continual learning task, our method leverages re-encoded labels of samples from the target category to guide weight updates, effectively scrubbing unwanted knowledge while preserving the rest of the model’s capacity. (3) Results and Conclusions: Experimental results on multiple benchmarks demonstrate that our method effectively eliminates targeted categories—achieving a recognition rate below 5%—while preserving the performance of retained classes within a 4% deviation from the original model. Full article
(This article belongs to the Special Issue Controllable and Reliable AI)
Show Figures

Figure 1

Back to TopTop