Submit to Mathematics Review for Mathematics Propose a Special Issue

Journal Browser

Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (31 August 2023) | Viewed by 17680

Share This Special Issue

Special Issue Editors

Prof. Dr. Zibin Zheng

E-Mail Website
Guest Editor

School of Software Engineering, Sun Yat-sen University, Zhuhai 510006, China
Interests: blockchain; software reliability; services computing; machine learning; big data analytics
Special Issues, Collections and Topics in MDPI journals

Dr. Ruoxi Jia

E-Mail Website
Guest Editor

Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24060, USA
Interests: machine learning; security; privacy; game theory
Special Issues, Collections and Topics in MDPI journals

Dr. Dan Li

E-Mail Website
Guest Editor

School of Software Engineering, Sun Yat-Sen University, Zhuhai 510006, China
Interests: mathematical modeling and statistical learning; anomaly detection and fault diagnosis; services-oriented computing; process mining; industrial Internet of Things; data management
Special Issues, Collections and Topics in MDPI journals

Dr. Yuxun Zhou

E-Mail Website
Guest Editor

Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA
Interests: statistical learning theory and paradigms for modern information rich; large-scale; human-involved systems
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Liang Xu

E-Mail Website
Guest Editor

School of Future Technology, Shanghai University, Shanghai 200444, China
Interests: control over communication; network control system; cyber-physical security and privacy; distributed control; data-driven control; neural networks and control
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Currently, new embedded technologies and interconnected networking advances in multiple domains based on new paradigms and heterogeneous technologies inevitably induce functional complexities of underlying engineering systems and, certainly, diverse vulnerabilities and risks may significantly grow according to new adaptations. Such trends have generated a need to further research the reliability, security and privacy of certain problems, calling for novel exploitations and guarantees for secure, resilient and dependable cohesion between theoretical algorithms and real-world engineering systems. For this reason, we are drawing special attention to the competitive advantages that recent prospering deep learning technologies and mathematical modeling approaches have to demonstrate, which can bring about original solution paths and advances related to the aforementioned challenges.

In this Special Issue, we are expecting a wide spectrum of research papers that cover relevant reliability, security and privacy issues in engineering, such as intrusion detection, cyber-attacks, critical data protection, situational awareness, incident responsiveness and system resilience. We welcome high-quality papers from both theory and application perspectives and embrace methodologies ranging from advanced deep learning technologies to efficient mathematical modeling in order to promote academic exchange between a wide array of scholars. As such, I am inviting you to submit an article to this Special Issue named “Advanced Deep Learning and Mathematical Modeling of Reliability, Security and Privacy” in Mathematics, a peer-reviewed journal. This Special Issue will focus on (but is not limited to) the following topics:

Mathematical modeling for reliability, security and privacy problems;
Innovative applications (healthcare, education, media, insurance, Internet of Things, smart city, industry, etc.) about risk management and reliability issues;
Data quality and sparse learning;
Mathematical solutions for representation learning;
Mathematical optimization techniques and its application for quality management;
Reliability, security and privacy analysis and requirements in engineering;
Vulnerabilities and risk assessment in networked systems;
Advanced threat models, cyber-crime or cyber-espionage;
Reliable, secure and private architectures by design;
Secure interoperability, mobility and coexistence between systems, including users;
Prevention, awareness and resilience models for advanced threats;
Data preservation and privacy models;
Trust management and trusted computing models;
Privacy issues and mitigation techniques;
Malware and intrusion detection techniques;
Mathematical and deep learning solutions for reliability problems in IoT and Industry 4.0.
…

Prof. Dr. Zibin Zheng
Dr. Ruoxi Jia
Dr. Dan Li
Dr. Yuxun Zhou
Dr. Liang Xu
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. Mathematics 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 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

deep learning
sparse learning
risk management
reliability
neural networks
anomaly detection
fault detection
cyber security
data privacy
data quality
mathematical modeling
knowledge-based systems

Published Papers (11 papers)

Download All Papers

Research

Jump to: Review

17 pages, 1305 KiB

Open AccessArticle

Malware Detection Based on the Feature Selection of a Correlation Information Decision Matrix

by Kai Lu, Jieren Cheng and Anli Yan

Mathematics 2023, 11(4), 961; https://0-doi-org.brum.beds.ac.uk/10.3390/math11040961 - 13 Feb 2023

Cited by 5 | Viewed by 1506

Abstract

Smartphone apps are closely integrated with our daily lives, and mobile malware has brought about serious security issues. However, the features used in existing traffic-based malware detection techniques have a large amount of redundancy and useless information, wasting the computational resources of training detection models. To overcome this drawback, we propose a feature selection method; the core of the method involves choosing selected features based on high irrelevance, thereby removing redundant features. Furthermore, artificial intelligence has implemented malware detection and achieved outstanding detection ability. However, almost all malware detection models in deep learning include pooling operations, which lead to the loss of some local information and affect the robustness of the model. We also propose designing a malware detection model for malicious traffic identification based on a capsule network. The main difference between the capsule network and the neural network is that the neuron outputs a scalar, while the capsule outputs a vector. It is more conducive to saving local information. To verify the effectiveness of our method, we verify it from three aspects. First, we use four popular machine learning algorithms to prove the effectiveness of the proposed feature selection method. Second, we compare the capsule network with the convolutional neural network to prove the superiority of the capsule network. Finally, we compare our proposed method with another state-of-the-art malware detection technique; our accuracy and recall increased by 9.71% and 20.18%, respectively. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

15 pages, 2006 KiB

Open AccessArticle

Privacy-Preserving Data Aggregation Scheme Based on Federated Learning for IIoT

by Fan Hongbin and Zhou Zhi

Mathematics 2023, 11(1), 214; https://0-doi-org.brum.beds.ac.uk/10.3390/math11010214 - 01 Jan 2023

Cited by 4 | Viewed by 1695

Abstract

The extensive application of the Internet of Things in the industrial field has formed the industrial Internet of Things (IIoT). By analyzing and training data from the industrial Internet of Things, intelligent manufacturing can be realized. Due to privacy concerns, the industrial data of various institutions cannot be shared, which forms data islands. To address this challenge, we propose a privacy-preserving data aggregation federated learning (PPDAFL) scheme for the IIoT. In federated learning, data aggregation is adopted to protect model changes and provide data security for industrial devices. By utilizing a practical Byzantine fault tolerance (PBFT) algorithm, each round selects an IIoT device from each aggregation area as the data aggregation and initialization node, and uses data aggregation to protect the model changes of a single user while resisting reverse analysis attacks from the industrial management center. The Paillier cryptosystem and secret sharing are combined to realize data security, fault tolerance, and data sharing. A security analysis and performance evaluation show that the scheme reduces computation and communication overheads while guaranteeing data privacy, message authenticity, and integrity. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

24 pages, 1684 KiB

Open AccessArticle

Distilled and Contextualized Neural Models Benchmarked for Vulnerable Function Detection

by Guanjun Lin, Heming Jia and Di Wu

Mathematics 2022, 10(23), 4482; https://0-doi-org.brum.beds.ac.uk/10.3390/math10234482 - 28 Nov 2022

Cited by 1 | Viewed by 1248

Abstract

Detecting vulnerabilities in programs is an important yet challenging problem in cybersecurity. The recent advancement in techniques of natural language understanding enables the data-driven research on automated code analysis to embrace Pre-trained Contextualized Models (PCMs). These models are pre-trained on the large corpus and can be fine-tuned for various downstream tasks, but their feasibility and effectiveness for software vulnerability detection have not been systematically studied. In this paper, we explore six prevalent PCMs and compare them with three mainstream Non-Contextualized Models (NCMs) in terms of generating effective function-level representations for vulnerability detection. We found that, although the detection performance of PCMs outperformed that of the NCMs, training and fine-tuning PCMs were computationally expensive. The budgets for deployment and inference are also considerable in practice, which may prevent the wide adoption of PCMs in the field of interest. However, we discover that, when the PCMs were compressed using the technique of knowledge distillation, they achieved similar detection performance but with significantly improved efficiency compared with their uncompressed counterparts when using 40,000 synthetic C functions for fine-tuning and approximately 79,200 real-world C functions for training. Among the distilled PCMs, the distilled CodeBERT achieved the most cost-effective performance. Therefore, we proposed a framework encapsulating the Distilled CodeBERT for an end-to-end Vulnerable function Detection (named DistilVD). To examine the performance of the proposed framework in real-world scenarios, DistilVD was tested on four open-source real-world projects with a small amount of training data. Results showed that DistilVD outperformed the five baseline approaches. Further evaluations on multi-class vulnerability detection also confirmed the effectiveness of DistilVD for detecting various vulnerability types. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

19 pages, 1903 KiB

Open AccessArticle

Cross Domain Data Generation for Smart Building Fault Detection and Diagnosis

by Dan Li, Yudong Xu, Yuxun Zhou, Chao Gou and See-Kiong Ng

Mathematics 2022, 10(21), 3970; https://0-doi-org.brum.beds.ac.uk/10.3390/math10213970 - 26 Oct 2022

Viewed by 1198

Abstract

Benefiting extensively from the Internet of Things (IoT) and sensor network technologies, the modern smart building achieves thermal comfort. It prevents energy wastage by performing automatic Fault Detection and Diagnosis (FDD) to maintain the good condition of its air-conditioning systems. Often, real-time multi-sensor measurements are collected, and supervised learning algorithms are adopted to exploit the data for an effective FDD. A key issue with the supervised methods is their dependence on well-labeled fault data, which is difficult to obtain in many real-world scenarios despite the abundance of unlabelled sensor data. Intuitively, the problem can be greatly alleviated if some well-labeled fault data collected under a particular setting can be re-used and transferred to other cases where labeled fault data is challenging or costly. Bearing this idea, we proposed a novel Adversarial Cross domain Data Generation (ACDG) framework to impute missing fault data for building fault detection and diagnosis where labeled data is costly. Unlike traditional Transfer Learning (TL)-related applications that adapt models or features learned in the source domain to the target domain, ACDG essentially “generates” the unknown sensor data for the target setting (target domain). This is accomplished by capturing the data patterns and common knowledge from known counterparts in the other setting (source domain), the inter-domain knowledge, and the intra-domain relations. The proposed ACDG framework is tested with the real-world Air Handling Unit (AHU) fault dataset of the ASHRAE Research Project 1312. Extensive experimental results on the cross-domain AHU fault data showed the effectiveness of ACDG in supplementing the data for a missing fault category by exploiting the underlying commonalities between different domain settings. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

22 pages, 2698 KiB

Open AccessArticle

Intelligent Bearing Fault Diagnosis Based on Open Set Convolutional Neural Network

by Bo Zhang, Caicai Zhou, Wei Li, Shengfei Ji, Hengrui Li, Zhe Tong and See-Kiong Ng

Mathematics 2022, 10(21), 3953; https://0-doi-org.brum.beds.ac.uk/10.3390/math10213953 - 24 Oct 2022

Cited by 5 | Viewed by 1562

Abstract

Traditional data-driven intelligent fault diagnosis methods have been successfully developed under the closed set assumption (CSA). CSA-based fault diagnosis assumes that the fault types in the test set are consistent with that in the training set, which can achieve high accuracy, but this is generally not valid in real-world industrial applications where the collection of data in industrial applications is often limited. As it is unrealistic to assume that the training set will cover all fault types, the application of the fault classifier may fail when the test set contains unknown fault types because the probability of input samples belonging to unknown types cannot be obtained. To solve the problem of how unknown fault types may be accurately identified, this paper further studies the open set assumption (OSA) fault diagnosis. We propose an open set convolutional neural network (OS-CNN) method and apply our OS-CNN model to an improved OpenMax method as a deep network to accurately detect unknown fault types. The overall performance was significantly improved as our OS-CNN model was able to effectively tighten the boundary of known classes and limit the open-space risk for the OpenMax method based on distance modeling. The overall effectiveness of the proposed method was verified by experimental studies based on four different bearing datasets. Compared with state-of-the-art OSA fault diagnosis method, our method cannot only realize the correct classification of the known fault classes, but it can also accurately detect the unknown fault classes. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

17 pages, 4015 KiB

Open AccessArticle

Bearing Fault Diagnosis Based on Discriminant Analysis Using Multi-View Learning

by Zhe Tong, Wei Li, Bo Zhang, Haifeng Gao, Xinglong Zhu and Enrico Zio

Mathematics 2022, 10(20), 3889; https://0-doi-org.brum.beds.ac.uk/10.3390/math10203889 - 20 Oct 2022

Cited by 2 | Viewed by 1155

Abstract

Bearing fault diagnosis has been a challenge in rotating machinery and has gained considerable attention. In order to correctly classify faults, the conventional fault diagnosis methods are mostly based on vibration signals. However, features extracted from a single view of vibration signals may leave out useful information, which can cause the incompleteness of intrinsic information and increase the risk of the performance degradation of fault classifications. In this paper, a novel bearing fault diagnosis method, discriminant analysis using multi-view learning (DAML), is proposed to tackle this issue. Multi-view datasets referring to vibration and acoustic signals are obtained by carrying out a fast Fourier transform (FFT). Then, multi-view feature (MVF) representation, including view-invariant and category discriminative information in a common subspace, is achieved based on canonical correlation analysis (CCA) and uncorrelated linear discriminant analysis (ULDA). Ultimately, with the help of the K-nearest neighbor (KNN) classifier built on the multi-view features, bearing faults are identified. The extensive experimental results show that DAML can identify the bearing fault accurately and outperforms other competitive approaches. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

18 pages, 12947 KiB

Open AccessArticle

Robustness Learning via Inference-Softmax Cross Entropy in Misaligned Distribution of Image

by Bingbing Song, Ruxin Wang, Wei He and Wei Zhou

Mathematics 2022, 10(19), 3716; https://0-doi-org.brum.beds.ac.uk/10.3390/math10193716 - 10 Oct 2022

Cited by 2 | Viewed by 1285

Abstract

Adversarial examples easily mislead vision systems based on deep neural networks (DNNs) trained with softmax cross entropy (SCE) loss. The vulnerability of DNN comes from the fact that SCE drives DNNs to fit on the training examples, whereas the resultant feature distributions between the training and adversarial examples are unfortunately misaligned. Several state-of-the-art methods start from improving the inter-class separability of training examples by modifying loss functions, where we argue that the adversarial examples are ignored, thus resulting in a limited robustness to adversarial attacks. In this paper, we exploited the inference region, which inspired us to apply margin-like inference information to SCE, resulting in a novel inference-softmax cross entropy (I-SCE) loss, which is intuitively appealing and interpretable. The inference information guarantees that it is difficult for neural networks to cross the decision boundary under an adversarial attack, and guarantees both the inter-class separability and the improved generalization to adversarial examples, which was further demonstrated and proved under the min-max framework. Extensive experiments show that the DNN models trained with the proposed I-SCE loss achieve a superior performance and robustness over the state-of-the-arts under different prevalent adversarial attacks; for example, the accuracy of I-SCE is

63%

higher than SCE under the

P G D_{50}^{u n}

attack on the MNIST dataset. These experiments also show that the inference region can effectively solve the misaligned distribution. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

17 pages, 4381 KiB

Open AccessArticle

The Synergy of Double Neural Networks for Bridge Bidding

by Xiaoyu Zhang, Rongheng Lin, Yuchang Bo and Fangchun Yang

Mathematics 2022, 10(17), 3187; https://0-doi-org.brum.beds.ac.uk/10.3390/math10173187 - 03 Sep 2022

Viewed by 2103

Abstract

Artificial intelligence (AI) has made many breakthroughs in the perfect information game. Nevertheless, Bridge, a multiplayer imperfect information game, is still quite challenging. Bridge consists of two parts: bidding and playing. Bidding accounts for about 75% of the game and playing for about 25%. Expert-level teams are generally indistinguishable at the playing level, so bidding is the more decisive factor in winning or losing. The two teams can communicate using different systems during the bidding phase. However, existing bridge bidding models focus on at most one bidding system, which does not conform to the real game rules. This paper proposes a deep reinforcement learning model that supports multiple bidding systems, which can compete with players using different bidding systems and exchange hand information normally. The model mainly comprises two deep neural networks: a bid selection network and a state evaluation network. The bid selection network can predict the probabilities of all bids, and the state evaluation network can directly evaluate the optional bids and make decisions based on the evaluation results. Experiments show that the bidding model is not limited by a single bidding system and has superior bidding performance. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

20 pages, 957 KiB

Open AccessArticle

Scalable Multi-Party Privacy-Preserving Gradient Tree Boosting over Vertically Partitioned Dataset with Outsourced Computations

by Kennedy Edemacu and Jong Wook Kim

Mathematics 2022, 10(13), 2185; https://0-doi-org.brum.beds.ac.uk/10.3390/math10132185 - 23 Jun 2022

Cited by 1 | Viewed by 1022

Abstract

Due to privacy concerns, multi-party gradient tree boosting algorithms have become widely popular amongst machine learning researchers and practitioners. However, limited existing works have focused on vertically partitioned datasets, and the few existing works are either not scalable or tend to leak information. Thus, in this work, we propose SSXGB, which is a scalable and acceptably secure multi-party gradient tree boosting framework for vertically partitioned datasets with partially outsourced computations. Specifically, we employ an additive homomorphic encryption (HE) scheme for security. We design two sub-protocols based on the HE scheme to perform non-linear operations associated with gradient tree boosting algorithms. Next, we propose secure training and prediction algorithms under the SSXGB framework. Then, we provide theoretical security and communication analysis for the proposed framework. Finally, we evaluate the performance of the framework with experiments using two real-world datasets. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

18 pages, 5426 KiB

Open AccessArticle

Online Bearing Fault Diagnosis Based on Packet Loss Influence-Inspired Retransmission Mechanism

by Zhe Tong, Wei Li, Enrico Zio, Bo Zhang and Gongbo Zhou

Mathematics 2022, 10(9), 1422; https://0-doi-org.brum.beds.ac.uk/10.3390/math10091422 - 23 Apr 2022

Cited by 2 | Viewed by 1128

Abstract

Vibration response has been extensively used for fault diagnosis to ensure the smooth operation of mechanical systems. However, the data for vibration condition monitoring may be misconstrued due to channel quality issues and external disturbances. In particular, data packet losses that often occur during transmission can cause spectral structure distortion, and as multiple sensing nodes are often employed for condition monitoring, the differences in the spectral structure distortions for different sensing nodes can be significant. While retransmission can reduce packet loss, it is difficult to achieve good performance under the complex conditions. Excessive or insufficient retransmission of data streams can result in unacceptable delays or errors for online fault diagnosis. In this paper, we propose a Packet Loss Influence-inspired Retransmission Mechanism (PLIRM) to address this problem and improve the online diagnostic efficiency. First, we devise a scheme for zero padding based on packet loss model (ZPPL) to preserve intrinsic properties of frequency domain. Then, we formulate a dynamic retransmission scheme generated based on the optimal packet loss mode to minimize the effects of spectral structure distortions. To ensure that the data stream that is most sensitive to a fault will be preferentially transmitted, we apply a priority setting trick using maximum mean discrepancy (MMD) to evaluate the spectral structure discrepancies between a data stream and the historical datasets. We evaluate the retransmission scheme using a fault diagnosis model based on K-nearest neighbor (KNN) for timely online bearing fault diagnosis. Extensive experimental results showed that the proposed method can accurately identify the bearing faults in a timely manner, outperforming competitive approaches under packet loss condition. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures

Figure 1

Review

Jump to: Research

43 pages, 892 KiB

Open AccessReview

The Geometry of Feature Space in Deep Learning Models: A Holistic Perspective and Comprehensive Review

by Minhyeok Lee

Mathematics 2023, 11(10), 2375; https://0-doi-org.brum.beds.ac.uk/10.3390/math11102375 - 19 May 2023

Cited by 5 | Viewed by 2225

Abstract

As the field of deep learning experiences a meteoric rise, the urgency to decipher the complex geometric properties of feature spaces, which underlie the effectiveness of diverse learning algorithms and optimization techniques, has become paramount. In this scholarly review, a comprehensive, holistic outlook on the geometry of feature spaces in deep learning models is provided in order to thoroughly probe the interconnections between feature spaces and a multitude of influential factors such as activation functions, normalization methods, and model architectures. The exploration commences with an all-encompassing examination of deep learning models, followed by a rigorous dissection of feature space geometry, delving into manifold structures, curvature, wide neural networks and Gaussian processes, critical points and loss landscapes, singular value spectra, and adversarial robustness, among other notable topics. Moreover, transfer learning and disentangled representations in feature space are illuminated, accentuating the progress and challenges in these areas. In conclusion, the challenges and future research directions in the domain of feature space geometry are outlined, emphasizing the significance of comprehending overparameterized models, unsupervised and semi-supervised learning, interpretable feature space geometry, topological analysis, and multimodal and multi-task learning. Embracing a holistic perspective, this review aspires to serve as an exhaustive guide for researchers and practitioners alike, clarifying the intricacies of the geometry of feature spaces in deep learning models and mapping the trajectory for future advancements in this enigmatic and enthralling domain. Full article

(This article belongs to the Special Issue Advanced Deep Learning and Mathematical Modeling for Reliability, Security and Privacy Problems in Engineering)

► Show Figures