Submit to Special Issue Submit Abstract to Special Issue Review for Electronics Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy

Print Special Issue Flyer
Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 20 September 2026 | Viewed by 3070

Share This Special Issue

Editors

Dr. Ziyang He

E-Mail Website
Guest Editor

School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, China
Interests: deep learning; federated learning; IoT security; privacy protection

Prof. Dr. Yangjie Cao

E-Mail Website
Guest Editor

School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, China
Interests: AI security; machine intelligence and human–computer interaction; intelligent big data processing; cloud computing and high-performance computing
Special Issues, Collections and Topics in MDPI journals

Dr. Minglin Liu

E-Mail Website
Guest Editor

School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450001, China
Interests: information hiding; AI security; steganography; watermarking

Special Issue Information

Dear Colleagues,

The rapid advancement and widespread adoption of Artificial Intelligence (AI) have profoundly transformed application development across various domains. While offering unprecedented capabilities, this integration has introduced significant challenges in ensuring security and privacy. AI systems themselves can be vulnerable to attacks such as data poisoning, adversarial examples, and model inversion, while their deployment raises critical concerns regarding data privacy, algorithmic bias, and accountability. Building AI that is not only intelligent but also trustworthy—robust, secure, fair, and transparent—has, therefore, become an imperative for achieving sustainable and safe technological progress.

This Special Issue will compile cutting-edge research and innovative solutions dedicated to the development and implementation of trustworthy AI with a specific focus on application security and privacy. We seek contributions that address the fundamental principles, architectural designs, and practical implementations of AI systems that can defend against evolving threats, protect sensitive data, and operate reliably in real-world scenarios. Our goal is to foster discussions on holistic frameworks that integrate security and privacy into the very fabric of AI models and systems.

Topics of interest for this Special Issue include, but are not limited to, the following:

Explainable and Transparent AI for Security Analysis;
Adversarial Machine Learning and Robust Defense Mechanisms;
Privacy-Preserving AI Techniques (e.g., Federated Learning, Differential Privacy);
AI-Driven Information Hiding and Steganography;
Secure AI Architecture and System Design;
AI for Threat Detection and Intrusion Prevention;
Trustworthy AI in Critical Applications (e.g., Healthcare, IoT);
AI-Powered Authentication and Access Control;
Security of AI Models Against Data Poisoning and Model Inversion;
Covert Communication and Data Protection Using Generative Models;
Detection of Steganography and Deepfakes;
Integration of Hardware Security with AI Workflows;
Benchmarks and Tools for Trustworthy AI Implementation.

We invite researchers, practitioners, and industry experts to submit original research articles, comprehensive reviews, and insightful case studies that contribute to the advancement of trustworthy AI in securing applications and safeguarding privacy.

Dr. Ziyang He
Dr. Yangjie Cao
Dr. Minglin Liu
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly 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 2400 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

trustworthy AI
AI security
data poisoning defense
membership inference attacks
adversarial machine learning
privacy-preserving
information hiding
federated learning
digital steganography
explainable AI (XAI) for security
AI for intrusion detection

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 (5 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

45 pages, 10830 KB

Open AccessArticle

iMediFood-Shield: Secure Edge AI for Food and Medication Interaction Screening

by Sai Sri Harsha Chakravarthula, Indira Devi Siripurapu, Laavanya Rachakonda, Saraju P. Mohanty and Elias Kougianos

Electronics 2026, 15(17), 3799; https://doi.org/10.3390/electronics15173799 - 24 Aug 2026

Abstract

Food–medication interactions can occur when medicines are taken with foods, drinks, herbs, or supplements that influence drug absorption, exposure, or activity. Screening these combinations is challenging because the available evidence is imbalanced, prescription text may be recognized incorrectly, unsupported inputs may produce unreliable predictions, and altered software artifacts may change the recommendation presented to the user. iMediFood-Shield addresses these concerns through an evidence-first edge-AI framework that combines structured diet–drug interaction evidence, prescription-assisted medication confirmation, coverage-aware rejection, calibrated five-class prediction, false-safe-aware confidence gating, and software-based tamper-evident verification. The DDID preparation process began with 23,950 evidence records and produced 16,644 canonical medication–food/herb pairs, including 16,165 single-effect model-eligible pairs and 479 multi-effect conflict pairs. A leakage-free 70%–15%–15% split was applied after canonicalization, and the deployed lookup was restricted to training-supported and conflict records. On the operational locked-test AI branch of 2259 supported unseen pairs, the final calibrated LinearSVC with the validation-selected MedSafe-GATE threshold of 0.65 achieved 91.72% accuracy, 80.57% balanced accuracy, and a macro F1-score of 0.8359. The gate reduced calibrated false-safe predictions from 55 to 28, corresponding to a 49.09% reduction and a final false-safe rate of 1.35% among interaction-bearing AI-branch pairs. RxOCR-Guard achieved 94.67% candidate recall and 100.00% candidate precision on a controlled synthetic prescription benchmark, while mandatory user confirmation was retained because top-1 candidate accuracy was 51.33%. The unchanged baseline and all ten adverse software-bundle conditions produced the expected verification outcomes for artifact-modification, missing-file, key-mismatch, manifest-alteration, and rollback cases. Raspberry Pi deployment reproduced all 2259 reference predictions without mismatch, completed covered AI inference in 1.737 ms on average, and verified the protected software bundle in 80.249 ms on average. These results show that iMediFood-Shield can combine evidence-grounded screening, conservative AI decision control, prescription confirmation, and software-integrity verification within a resource-constrained edge research prototype. Full article

(This article belongs to the Special Issue Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy)

► Show Figures

Figure 1

30 pages, 5625 KB

Open AccessArticle

cStick 2.0: An IoMT-Edge-Based Vision-Enabled Smart System for Personalized Fall Prediction and Detection

by Laavanya Rachakonda, Sai Sri Harsha Chakravarthula, Saraju P. Mohanty and Elias Kougianos

Electronics 2026, 15(15), 3375; https://doi.org/10.3390/electronics15153375 - 1 Aug 2026

Viewed by 220

Abstract

Falls among older adults can cause serious injury and loss of independence. cStick 2.0 is a vision-enabled, IoMT-edge based smart walking-stick prototype that combines multimodal fall-risk classification with embedded obstacle awareness. The fall-risk classifiers were evaluated using a 9670-record development dataset, on which the compact DNN achieved 95.40% accuracy, 92.35% balanced accuracy, a macro F1-score of 93.90%, and a ROC-AUC of 97.44%. The Arduino Nicla Vision obstacle module used an INT8 Edge Impulse model with centroid-based direction assignment and time-of-flight distance sensing; 144 controlled trials produced 75.00% obstacle-presence accuracy at approximately 19–20 FPS. Sensor acquisition, GPS, display output, buzzer response, and CSV record accumulation were demonstrated at a prototype level. Synchronized older-adult evaluation, device-to-application communication, secure caregiver services, multimodal accessibility feedback, and longitudinal personalization remain future validation stages. Full article

(This article belongs to the Special Issue Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy)

► Show Figures

Figure 1

20 pages, 6356 KB

Open AccessArticle

A Low-Complexity CW Radar for Detecting High-Precision Tiny Vibration

by Chao Wang, Yiming Wang, Xiaoyue Wei, Jinpeng Shi, Zili Jiao, Pengsong Duan and Yangjie Cao

Electronics 2026, 15(9), 1820; https://doi.org/10.3390/electronics15091820 - 24 Apr 2026

Viewed by 506

Abstract

Research on methods for detecting microwave-based noncontact vibration has garnered significant attention in recent years. To simplify system complexity and reduce costs, which would enable broader application of radar technology in daily life, we propose a low-complexity, high-precision continuous-wave (CW) radar system for noncontact vibration detection. This system employs a hardware-based approach for phase comparison to extract vibration information, enabling simultaneous detection of both vibration amplitude and frequency under a CW radar architecture. In this study, we establish a phase discrimination error model to characterize the inconsistent detection sensitivity of the hardware phase comparator in different phase intervals, and we further propose a phase compensation scheme to mitigate the nonlinearity of phase discrimination and the “null-point” problem in continuous phase comparison, consequently improving the sensitivity and precision of the proposed radar system. Through loudspeaker vibration and experiments on human vital signs, the system maintains a vibration amplitude detection accuracy above 90.3% within 1.8 m while achieving respiratory rate and heartbeat rate detection accuracies of 96.34% and 98.02%, respectively. Full article

(This article belongs to the Special Issue Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy)

► Show Figures

Figure 1

25 pages, 769 KB

Open AccessArticle

Standard-Oriented Architecture for AI-Powered Information Security Risk Management

by Oleksii Chalyi, Kęstutis Driaunys, Šarūnas Grigaliūnas and Rasa Brūzgienė

Electronics 2026, 15(6), 1282; https://doi.org/10.3390/electronics15061282 - 19 Mar 2026

Viewed by 1163

Abstract

This paper presents a standard-oriented architecture for automating information security risk management (ISRM) using artificial intelligence. The study first evaluates eight international frameworks (including COBIT 2019, NIST SP 800-53, and ISO 31000) for automation suitability, identifying ISO/IEC 27005 as the optimal structural foundation. Based on these findings, an architecture integrating Natural Language Processing and machine learning to automate risk identification, assessment, and treatment is proposed. A core component is a decision-making module that combines expert reasoning with a Multi-LLM consensus mechanism to ensure reliability. To provide exploratory support for the proposed architecture, a comparative study using five state-of-the-art Large Language Models (ChatGPT, Gemini Advanced, Grok, Microsoft Copilot, and DeepSeek Chat) was conducted on a standardized risk identification task. The results highlight strong cross-model consensus patterns, providing exploratory evidence that LLMs may support expert-informed risk identification and reasoning tasks while acknowledging the current limitations in complex reasoning. This approach proposes a transparent architectural foundation for AI-driven ISRM whose scalability must be established through future prototype-based evaluation, thereby bridging the gap between rigid compliance standards and generative AI capabilities. Full article

(This article belongs to the Special Issue Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy)

► Show Figures

Figure 1

22 pages, 2090 KB

Open AccessArticle

Mini-Hide: Generative Image Steganography via Flip Watermarking for Reducing BER

by Rixuan Qiu, Zhiyuan Luo, Ruixiang Fan, Na Cao, Yuan Wang and Cong Yang

Electronics 2026, 15(5), 939; https://doi.org/10.3390/electronics15050939 - 25 Feb 2026

Viewed by 746

Abstract

Generative image steganography is a key technology for secure information transmission, but existing deep learning-based generative steganographic methods suffer from an extremely high bit error rate (BER) and degraded steganographic image quality in low-bit-rate embedding tasks in which secret information needs duplication or padding to match the model input size. In addition, it is difficult to balance BER reduction and imperceptibility of stego-images. To address these issues, this paper proposes a novel generative image steganography algorithm based on flip watermarking, with the core novelty of designing a mirror flipping preprocessing mechanism to achieve a redundant watermark and eliminate information errors caused by duplication or padding, and constructing an end-to-end Mini-Hide steganographic framework to integrate flip watermarking with generative steganography for the first time. Specifically, the proposed method first converts the binary bitstream of secret information into a square matrix, and performs vertical, horizontal and vertical–horizontal mirror flipping on the matrix to form a redundant basic watermark, which is then expanded to a secret image with the same size as the cover image. After that, the secret image is preprocessed by a preparation network and then input into an encoding network together with the cover image to generate a stego-image. Finally, the generated stego-image is input into the decoding network to extract the secret image. Subsequently, the inverse operation of flip watermarking is performed on the extracted secret image to recover the original binary bitstream. Extensive experiments are conducted on the public COCO dataset (

256 \times 256

pixels) with BER, PSNR, and SSIM, and the proposed method is compared with state-of-the-art generative steganographic methods. Quantitative results show that the proposed method achieves a

0 %

BER for secret information of

8 \times 8

64 \times 64

bits, and the BER is only

0.00002 %

for

256 \times 256

-bit secret information; the PSNR of stego-images reaches 37.75 dB, and the SSIM hits 0.96, which are 7.07 dB and 0.02 higher than those of the classic HiDDeN method (

64 \times 64

bit) respectively. We also validated the flip watermark module by integrating into other methods; the results also show that the PSNR of FNNS-D is improved by 13.12 dB (

256 \times 256

), and the BER of SteganoGAN is reduced by

99.99 %

(

256 \times 256

bit). In addition, the proposed method breaks the embedding size limit of HiDDeN (≤

64 \times 64

bit) and supports up to

256 \times 256

-bit secret information embedding with stable performance. This work significantly reduces the BER of generative image steganography while improving the visual quality of stego-images, provides a new preprocessing and optimization scheme for low-BER generative steganographic algorithm design, and also offers a universal lightweight module for performance improvement of existing steganographic methods, which has important theoretical and practical significance for enhancing the security and reliability of covert information transmission in the field of information security. Full article

(This article belongs to the Special Issue Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy)

► Show Figures

Journal Menu

Journal Browser

Towards Trustworthy AI: Techniques, Architectures, and Applications for Security and Privacy

Share This Special Issue

Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (5 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI