Submit to Cryptography Review for Cryptography Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Cybersecurity, Cryptography, and Machine Learning

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Cryptography (ISSN 2410-387X).

Deadline for manuscript submissions: closed (30 October 2021) | Viewed by 15027

Share This Special Issue

Special Issue Editor

Dr. Hossein Sayadi

E-Mail Website
Guest Editor

Department of Computer Engineering & Computer Science California State University, Long Beach, CA, USA
Interests: computer systems cybersecurity; machine learning; hardware security
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Cybersecurity for the past decades has been in the front line of global attention as an increasingly critical area of concern. The ever-expanding complexity of modern computing systems has resulted in the growth of security vulnerabilities, making such systems appealing targets for sophisticated cyber-attacks. The rapid development of computing devices in various domains such as high-performance computing, cloud/edge/fog computing, embedded systems, mobile platforms, and Internet-of-Things (IoT) combined with emerging 5G cellular networks further exacerbates the impact of cybersecurity threats, calling for efficient security countermeasures to protect legitimate users from these attacks. Cryptography is one of the most important tools that has been widely deployed by researchers and practitioners in academia and industry to build secure information technology infrastructures ensuring the confidentiality of data and protecting users’ information from unauthorized access. Furthermore, advancements in the area of artificial intelligence and machine learning, driven by a significant increase in the size of data getting generated and transferred over networks, have resulted in successful applications of machine learning algorithms to automatically identify and analyze security threats protecting organizations against evolving cyber-attacks. As a result, the goal of this Special Issue is to highlight the latest technologies and solutions that focus on theory, analysis, experiments, or application of cybersecurity, cryptography, and machine learning in modern computing systems. Papers dealing with systematization of knowledge and survey papers are also welcome. Specific topics of interest include, but are not limited to:

Cryptographic primitives and protocols
Applied cryptography for cybersecurity
Application of machine learning for cybersecurity and cryptography
Artificial intelligence security (e.g., adversarial machine learning)
Network security
Intrusion detection systems
Malware detection and identification
Advanced persistent threats analysis
Denial-of-Service (DoS) attacks and defenses
Side-channel attacks analysis, detection, and mitigation techniques
Hardware security and trust
Formal methods for secure hardware and software
Detection and prevention of hardware trojans
Hardware and software reverse engineering
Fault attacks and countermeasures
FPGA design security
Mobile security
Internet-of-Things (IoT) security
Vulnerability analysis techniques
Cyber physical systems security and resilience
Security and privacy for cloud, edge, and fog computing
Cybersecurity metrics and assessment

Dr. Hossein Sayadi
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. Cryptography is an international peer-reviewed open access quarterly 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

Cybersecurity
Cryptography
Machine Learning
Threats and Countermeasures
Intrusion Detection
Side-Channel Attacks
Malware
Adversarial Learning
Physical Attacks
IoT Security
Fault attacks

Published Papers (3 papers)

Download All Papers

Research

Jump to: Review

25 pages, 2260 KiB

Open AccessArticle

Towards Accurate Run-Time Hardware-Assisted Stealthy Malware Detection: A Lightweight, yet Effective Time Series CNN-Based Approach

by Hossein Sayadi, Yifeng Gao, Hosein Mohammadi Makrani, Jessica Lin, Paulo Cesar Costa, Setareh Rafatirad and Houman Homayoun

Cryptography 2021, 5(4), 28; https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5040028 - 17 Oct 2021

Cited by 10 | Viewed by 3952

Abstract

According to recent security analysis reports, malicious software (a.k.a. malware) is rising at an alarming rate in numbers, complexity, and harmful purposes to compromise the security of modern computer systems. Recently, malware detection based on low-level hardware features (e.g., Hardware Performance Counters (HPCs) information) has emerged as an effective alternative solution to address the complexity and performance overheads of traditional software-based detection methods. Hardware-assisted Malware Detection (HMD) techniques depend on standard Machine Learning (ML) classifiers to detect signatures of malicious applications by monitoring built-in HPC registers during execution at run-time. Prior HMD methods though effective have limited their study on detecting malicious applications that are spawned as a separate thread during application execution, hence detecting stealthy malware patterns at run-time remains a critical challenge. Stealthy malware refers to harmful cyber attacks in which malicious code is hidden within benign applications and remains undetected by traditional malware detection approaches. In this paper, we first present a comprehensive review of recent advances in hardware-assisted malware detection studies that have used standard ML techniques to detect the malware signatures. Next, to address the challenge of stealthy malware detection at the processor’s hardware level, we propose StealthMiner, a novel specialized time series machine learning-based approach to accurately detect stealthy malware trace at run-time using branch instructions, the most prominent HPC feature. StealthMiner is based on a lightweight time series Fully Convolutional Neural Network (FCN) model that automatically identifies potentially contaminated samples in HPC-based time series data and utilizes them to accurately recognize the trace of stealthy malware. Our analysis demonstrates that using state-of-the-art ML-based malware detection methods is not effective in detecting stealthy malware samples since the captured HPC data not only represents malware but also carries benign applications’ microarchitectural data. The experimental results demonstrate that with the aid of our novel intelligent approach, stealthy malware can be detected at run-time with 94% detection performance on average with only one HPC feature, outperforming the detection performance of state-of-the-art HMD and general time series classification methods by up to 42% and 36%, respectively. Full article

(This article belongs to the Special Issue Cybersecurity, Cryptography, and Machine Learning)

► Show Figures

Figure 1

21 pages, 5845 KiB

Open AccessArticle

A Delay-Based Machine Learning Model for DMA Attack Mitigation

by Yutian Gui, Chaitanya Bhure, Marcus Hughes and Fareena Saqib

Cryptography 2021, 5(3), 18; https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5030018 - 27 Jul 2021

Cited by 4 | Viewed by 3719

Abstract

Direct Memory Access (DMA) is a state-of-the-art technique to optimize the speed of memory access and to efficiently use processing power during data transfers between the main system and a peripheral device. However, this advanced feature opens security vulnerabilities of access compromise and to manipulate the main memory of the victim host machine. The paper outlines a lightweight process that creates resilience against DMA attacks minimal modification to the configuration of the DMA protocol. The proposed scheme performs device identification of the trusted PCIe devices that have DMA capabilities and constructs a database of profiling time to authenticate the trusted devices before they can access the system. The results show that the proposed scheme generates a unique identifier for trusted devices and authenticates the devices. Furthermore, a machine learning–based real-time authentication scheme is proposed that enables runtime authentication and share the results of the time required for training and respective accuracy. Full article

(This article belongs to the Special Issue Cybersecurity, Cryptography, and Machine Learning)

► Show Figures

Figure 1

Review

Jump to: Research

29 pages, 8557 KiB

Open AccessReview

Flash-Based Security Primitives: Evolution, Challenges and Future Directions

by Holden Gordon, Jack Edmonds, Soroor Ghandali, Wei Yan, Nima Karimian and Fatemeh Tehranipoor

Cryptography 2021, 5(1), 7; https://0-doi-org.brum.beds.ac.uk/10.3390/cryptography5010007 - 04 Feb 2021

Cited by 5 | Viewed by 5644

Abstract

Over the last two decades, hardware security has gained increasing attention in academia and industry. Flash memory has been given a spotlight in recent years, with the question of whether or not it can prove useful in a security role. Because of inherent process variation in the characteristics of flash memory modules, they can provide a unique fingerprint for a device and have thus been proposed as locations for hardware security primitives. These primitives include physical unclonable functions (PUFs), true random number generators (TRNGs), and integrated circuit (IC) counterfeit detection. In this paper, we evaluate the efficacy of flash memory-based security primitives and categorize them based on the process variations they exploit, as well as other features. We also compare and evaluate flash-based security primitives in order to identify drawbacks and essential design considerations. Finally, we describe new directions, challenges of research, and possible security vulnerabilities for flash-based security primitives that we believe would benefit from further exploration. Full article

(This article belongs to the Special Issue Cybersecurity, Cryptography, and Machine Learning)

► Show Figures