Sensors

2024

Jump to: 2023, 2022

33 pages, 2291 KiB

Open AccessArticle

Hardware-Efficient Configurable Ring-Oscillator-Based Physical Unclonable Function/True Random Number Generator Module for Secure Key Management

by Santiago Sánchez-Solano, Luis F. Rojas-Muñoz, Macarena C. Martínez-Rodríguez and Piedad Brox

Sensors 2024, 24(17), 5674; https://doi.org/10.3390/s24175674 - 31 Aug 2024

Viewed by 824

Abstract

The use of physical unclonable functions (PUFs) linked to the manufacturing process of the electronic devices supporting applications that exchange critical data over the Internet has made these elements essential to guarantee the authenticity of said devices, as well as the confidentiality and [...] Read more.

The use of physical unclonable functions (PUFs) linked to the manufacturing process of the electronic devices supporting applications that exchange critical data over the Internet has made these elements essential to guarantee the authenticity of said devices, as well as the confidentiality and integrity of the information they process or transmit. This paper describes the development of a configurable PUF/TRNG module based on ring oscillators (ROs) that takes full advantage of the structure of modern programmable devices offered by Xilinx 7 Series families. The proposed architecture improves the hardware efficiency with two main objectives. On the one hand, we perform an exhaustive statistical characterization of the results derived from the exploitation of RO configurability. On the other hand, we undertake the development of a new version of the module that requires a smaller amount of resources while considerably increasing the number of output bits compared to other proposals previously reported in the literature. The design as a highly parameterized intellectual property (IP) module connectable through a standard interface to a soft- or hard-core general-purpose processor greatly facilitates its integration into embedded solutions while accelerating the validation and characterization of this element on the same electronic device that implements it. The studies carried out reveal adequate values of reliability, uniqueness, and unpredictability when the module acts as a PUF, as well as acceptable levels of randomness and entropy when it acts as a true random number generator (TRNG). They also illustrate the ability to obfuscate and recover identifiers or cryptographic keys of up to 4096 bits using an implementation of the PUF/TRNG module that requires only an array of

4 \times 4

configurable logic blocks (CLBs) to accommodate the RO bank. Full article

► Show Figures

Figure 1

17 pages, 3234 KiB

Open AccessArticle

Secure Triggering Frame-Based Dynamic Power Saving Mechanism against Battery Draining Attack in Wi-Fi-Enabled Sensor Networks

by So-Yeon Kim, So-Hyun Park, Jung-Hoon Lee and Il-Gu Lee

Sensors 2024, 24(16), 5131; https://doi.org/10.3390/s24165131 - 8 Aug 2024

Viewed by 1000

Abstract

Wireless local area networks (WLANs) have recently evolved into technologies featuring extremely high throughput and ultra-high reliability. As WLANs are predominantly utilized in Internet of Things (IoT) and Wi-Fi-enabled sensor applications powered by coin cell batteries, these high-efficiency, high-performance technologies often cause significant [...] Read more.

Wireless local area networks (WLANs) have recently evolved into technologies featuring extremely high throughput and ultra-high reliability. As WLANs are predominantly utilized in Internet of Things (IoT) and Wi-Fi-enabled sensor applications powered by coin cell batteries, these high-efficiency, high-performance technologies often cause significant battery depletion. The introduction of the trigger frame-based uplink transmission method, designed to enhance network throughput, lacks adequate security measures, enabling attackers to manipulate trigger frames. Devices receiving such frames must respond immediately; however, if a device receives a fake trigger frame, it fails to enter sleep mode, continuously sending response signals and thereby increasing power consumption. This problem is specifically acute in next-generation devices that support multi-link operation (MLO), capable of simultaneous transmission and reception across multiple links, rendering them more susceptible to battery draining attacks than conventional single-link devices. To address this, this paper introduces a Secure Triggering Frame-Based Dynamic Power Saving Mechanism (STF-DPSM) specifically designed for multi-link environments. Experimental results indicate that even in a multi-link environment with only two links, the STF-DPSM improves energy efficiency by an average of approximately 55.69% over conventional methods and reduces delay times by an average of approximately 44.7% compared with methods that consistently utilize encryption/decryption and integrity checks. Full article

► Show Figures

Figure 1

17 pages, 34747 KiB

Open AccessArticle

Hierarchical Clustering via Single and Complete Linkage Using Fully Homomorphic Encryption

by Lynin Sokhonn, Yun-Soo Park and Mun-Kyu Lee

Sensors 2024, 24(15), 4826; https://doi.org/10.3390/s24154826 - 25 Jul 2024

Viewed by 700

Abstract

Hierarchical clustering is a widely used data analysis technique. Typically, tools for this method operate on data in its original, readable form, raising privacy concerns when a clustering task involving sensitive data that must remain confidential is outsourced to an external server. To [...] Read more.

Hierarchical clustering is a widely used data analysis technique. Typically, tools for this method operate on data in its original, readable form, raising privacy concerns when a clustering task involving sensitive data that must remain confidential is outsourced to an external server. To address this issue, we developed a method that integrates Cheon-Kim-Kim-Song homomorphic encryption (HE), allowing the clustering process to be performed without revealing the raw data. In hierarchical clustering, the two nearest clusters are repeatedly merged until the desired number of clusters is reached. The proximity of clusters is evaluated using various metrics. In this study, we considered two well-known metrics: single linkage and complete linkage. Applying HE to these methods involves sorting encrypted distances, which is a resource-intensive operation. Therefore, we propose a cooperative approach in which the data owner aids the sorting process and shares a list of data positions with a computation server. Using this list, the server can determine the clustering of the data points. The proposed approach ensures secure hierarchical clustering using single and complete linkage methods without exposing the original data. Full article

► Show Figures

Figure 1

19 pages, 630 KiB

Open AccessArticle

Efficiency and Security Evaluation of Lightweight Cryptographic Algorithms for Resource-Constrained IoT Devices

by Indu Radhakrishnan, Shruti Jadon and Prasad B. Honnavalli

Sensors 2024, 24(12), 4008; https://doi.org/10.3390/s24124008 - 20 Jun 2024

Viewed by 2893

Abstract

The IoT has become an integral part of the technological ecosystem that we all depend on. The increase in the number of IoT devices has also brought with it security concerns. Lightweight cryptography (LWC) has evolved to be a promising solution to improve [...] Read more.

The IoT has become an integral part of the technological ecosystem that we all depend on. The increase in the number of IoT devices has also brought with it security concerns. Lightweight cryptography (LWC) has evolved to be a promising solution to improve the privacy and confidentiality aspect of IoT devices. The challenge is to choose the right algorithm from a plethora of choices. This work aims to compare three different LWC algorithms: AES-128, SPECK, and ASCON. The comparison is made by measuring various criteria such as execution time, memory utilization, latency, throughput, and security robustness of the algorithms in IoT boards with constrained computational capabilities and power. These metrics are crucial to determine the suitability and help in making informed decisions on choosing the right cryptographic algorithms to strike a balance between security and performance. Through the evaluation it is observed that SPECK exhibits better performance in resource-constrained IoT devices. Full article

► Show Figures

Figure 1

2023

Jump to: 2024, 2022

22 pages, 5811 KiB

Open AccessArticle

A Privacy-Preserving Trajectory Publishing Method Based on Multi-Dimensional Sub-Trajectory Similarities

by Hua Shen, Yu Wang and Mingwu Zhang

Sensors 2023, 23(24), 9652; https://doi.org/10.3390/s23249652 - 6 Dec 2023

Cited by 1 | Viewed by 1144

Abstract

With the popularity of location services and the widespread use of trajectory data, trajectory privacy protection has become a popular research area. k-anonymity technology is a common method for achieving privacy-preserved trajectory publishing. When constructing virtual trajectories, most existing trajectory k-anonymity [...] Read more.

With the popularity of location services and the widespread use of trajectory data, trajectory privacy protection has become a popular research area. k-anonymity technology is a common method for achieving privacy-preserved trajectory publishing. When constructing virtual trajectories, most existing trajectory k-anonymity methods just consider point similarity, which results in a large dummy trajectory space. Suppose there are n similar point sets, each consisting of m points. The size of the space is then

m^{n}

. Furthermore, to choose suitable k− 1 dummy trajectories for a given real trajectory, these methods need to evaluate the similarity between each trajectory in the space and the real trajectory, leading to a large performance overhead. To address these challenges, this paper proposes a k-anonymity trajectory privacy protection method based on the similarity of sub-trajectories. This method not only considers the multidimensional similarity of points, but also synthetically considers the area between the historic sub-trajectories and the real sub-trajectories to more fully describe the similarity between sub-trajectories. By quantifying the area enclosed by sub-trajectories, we can more accurately capture the spatial relationship between trajectories. Finally, our approach generates

k - 1

dummy trajectories that are indistinguishable from real trajectories, effectively achieving k-anonymity for a given trajectory. Furthermore, our proposed method utilizes real historic sub-trajectories to generate dummy trajectories, making them more authentic and providing better privacy protection for real trajectories. In comparison to other frequently employed trajectory privacy protection methods, our method has a better privacy protection effect, higher data quality, and better performance. Full article

► Show Figures

Figure 1

18 pages, 3004 KiB

Open AccessArticle

Enhancing Security of Web-Based IoT Services via XSS Vulnerability Detection

by Jemin Kim and Joonseok Park

Sensors 2023, 23(23), 9407; https://doi.org/10.3390/s23239407 - 25 Nov 2023

Cited by 3 | Viewed by 1618

Abstract

The Internet of Things (IoT) technology is experiencing significant growth and integration into various aspects of daily life. With the rising number of connected devices, diverse security challenges are emerging as substantial threats to IoT. Cross-Site Scripting (XSS) is one of the major [...] Read more.

The Internet of Things (IoT) technology is experiencing significant growth and integration into various aspects of daily life. With the rising number of connected devices, diverse security challenges are emerging as substantial threats to IoT. Cross-Site Scripting (XSS) is one of the major security risks in web services and so is within the application layer of IoT. Many existing web applications remain susceptible to XSS vulnerabilities. In this paper, we propose an XSS detection scheme aimed at enhancing the security of IoT, particularly concerning web application services. To achieve this, we developed a framework for combining symbolic execution and dynamic taint analysis to provide a comprehensive security assessment. Our objective is to increase the ratio of vulnerability detection while avoiding false alarms and keeping the required analysis time as minimal. To realize our idea, we have defined an instrumentation scheme for taint analysis and concolic executions and automated the process of vulnerability detection for a web application. Our framework is capable of pinpointing the precise locations of security vulnerabilities and the exact input datasets at risk of XSS threats. Subsequently, the detected flaws can be easily removed. The experimental results demonstrate the validity of the proposed scheme. We achieved a detection rate of XSS threats of 90.62% using a test set of SecuriBench Micro and 69.11% using OWASP while showing 0% false positives. Full article

► Show Figures

Figure 1

15 pages, 1452 KiB

Open AccessArticle

K-XMSS and K-SPHINCS⁺: Enhancing Security in Next-Generation Mobile Communication and Internet Systems with Hash Based Signatures Using Korean Cryptography Algorithms

by Minjoo Sim, Siwoo Eum, Gyeongju Song, Yujin Yang, Wonwoong Kim and Hwajeong Seo

Sensors 2023, 23(17), 7558; https://doi.org/10.3390/s23177558 - 31 Aug 2023

Cited by 2 | Viewed by 1878

Abstract

As Mobile Communication and Internet Systems (MCIS) have rapidly developed, security issues related to MCIS have become increasingly important. Therefore, the development and research of security technologies for mobile communication and internet systems are actively being conducted. Hash-Based Signature (HBS) uses a hash [...] Read more.

As Mobile Communication and Internet Systems (MCIS) have rapidly developed, security issues related to MCIS have become increasingly important. Therefore, the development and research of security technologies for mobile communication and internet systems are actively being conducted. Hash-Based Signature (HBS) uses a hash function to construct a digital signature scheme, where its security is guaranteed by the collision resistance of the hash function used. To provide sufficient security in the post-quantum environment, the length of hash should be satisfied for the security requirement. Modern HBS can be classified into stateful and stateless schemes. Two representative stateful and stateless HBS are eXtended Merkle Signature Scheme(XMSS) and SPHINCS

^{+}

, respectively. In this paper, we propose two HBS schemes: K-XMSS and K-SPHINCS

^{+}

, which replace internal hash functions of XMSS and SPHINCS

^{+}

with Korean cryptography algorithms. K-XMSS is a stateful signature, while K-SPHINCS

^{+}

is its stateless counterpart. We showcase the reference implementation of K-XMSS and K-SPHINCS

^{+}

employing Lightweight Secure Hash (LSH) and two hash functions based on block ciphers (i.e., CHAM and LEA) as the internal hash function. In addition, K-XMSS and K-SPHINCS

^{+}

using Advanced Vector Extensions 2 (AVX2) have been provided, demonstrating that they can be optimized for better performance using advanced implementation techniques than previous approaches. Full article

► Show Figures

Figure 1

16 pages, 390 KiB

Open AccessArticle

Backward Compatible Identity-Based Encryption

by Jongkil Kim

Sensors 2023, 23(9), 4181; https://doi.org/10.3390/s23094181 - 22 Apr 2023

Cited by 2 | Viewed by 1516

Abstract

In this paper, we present a new identity-based encryption (IBE) system that is named Backward Compatible Identity-based Encryption (BC-IBE). Our BC-IBE is proposed to solve the problem caused by the out-of-synchronization between users’ private keys and ciphertexts. Encryption systems such as revocable IBE [...] Read more.

In this paper, we present a new identity-based encryption (IBE) system that is named Backward Compatible Identity-based Encryption (BC-IBE). Our BC-IBE is proposed to solve the problem caused by the out-of-synchronization between users’ private keys and ciphertexts. Encryption systems such as revocable IBE or revocable Attribute-based Encryption (ABE) often require updating private keys to revoke users after a certain time period. However, in those schemes, an updated key can be used to decrypt the ciphertexts created only during the current time period. Once the key is updated and the previous keys are removed, the user, the owner of the updated key, will lose access to the past ciphertexts. In our paper, we propose BC-IBE that supports backward compatibility, to solve this problem. In our proposed system, user’s private keys and ciphertexts can be updated periodically with time tags, and these processes can be used to revoke users who do not receive an updated key as the other revocable encryption does. However, in our proposed system, a private key newly issued to a user is backward compatible. This means that it decrypts not only the ciphertexts at the present time period but also all past ciphertexts. This implies that our proposed scheme guarantees the decryption of all encrypted data even if they are not synchronized. Compared to the existing revocable identity-based encryption system, our proposed BC-IBE has the advantage of simplifying key management and securely delegating ciphertext updates. Our proposed scheme only requires a single backward-compatible private key to decrypt all past ciphertexts created. Moreover, the ciphertext update process in our proposed scheme does not require any special privileges and does not require decryption. This means that this process can be securely delegated to a third-party server, such as a cloud server, and it prevents the potential leakage of secrets. For those reasons, BC-IBE is suitable for a system where users are more dynamic, such as the Internet-of-Things (IoT) network, or a system that regularly updates the data, like cloud data storage. In this paper, we provide the construction of BC-IBE and prove its formal security. Full article

► Show Figures

Figure 1

15 pages, 1384 KiB

Open AccessCommunication

Efficient L_p Distance Computation Using Function-Hiding Inner Product Encryption for Privacy-Preserving Anomaly Detection

by Dong-Hyeon Ryu, Seong-Yun Jeon, Junho Hong and Mun-Kyu Lee

Sensors 2023, 23(8), 4169; https://doi.org/10.3390/s23084169 - 21 Apr 2023

Cited by 1 | Viewed by 1907

Abstract

In Internet of Things (IoT) systems in which a large number of IoT devices are connected to each other and to third-party servers, it is crucial to verify whether each device operates appropriately. Although anomaly detection can help with this verification, individual devices [...] Read more.

In Internet of Things (IoT) systems in which a large number of IoT devices are connected to each other and to third-party servers, it is crucial to verify whether each device operates appropriately. Although anomaly detection can help with this verification, individual devices cannot afford this process because of resource constraints. Therefore, it is reasonable to outsource anomaly detection to servers; however, sharing device state information with outside servers may raise privacy concerns. In this paper, we propose a method to compute the

L_{p}

distance privately for even

p > 2

using inner product functional encryption and we use this method to compute an advanced metric, namely p-powered error, for anomaly detection in a privacy-preserving manner. We demonstrate implementations on both a desktop computer and Raspberry Pi device to confirm the feasibility of our method. The experimental results demonstrate that the proposed method is sufficiently efficient for use in real-world IoT devices. Finally, we suggest two possible applications of the proposed computation method for

L_{p}

distance for privacy-preserving anomaly detection, namely smart building management and remote device diagnosis. Full article

► Show Figures

Figure 1

14 pages, 1162 KiB

Open AccessArticle

Quantum Binary Field Multiplication with Optimized Toffoli Depth and Extension to Quantum Inversion

by Kyungbae Jang, Wonwoong Kim, Sejin Lim, Yeajun Kang, Yujin Yang and Hwajeong Seo

Sensors 2023, 23(6), 3156; https://doi.org/10.3390/s23063156 - 15 Mar 2023

Cited by 2 | Viewed by 2059

Abstract

The Shor’s algorithm can find solutions to the discrete logarithm problem on binary elliptic curves in polynomial time. A major challenge in implementing Shor’s algorithm is the overhead of representing and performing arithmetic on binary elliptic curves using quantum circuits. Multiplication of binary [...] Read more.

The Shor’s algorithm can find solutions to the discrete logarithm problem on binary elliptic curves in polynomial time. A major challenge in implementing Shor’s algorithm is the overhead of representing and performing arithmetic on binary elliptic curves using quantum circuits. Multiplication of binary fields is one of the critical operations in the context of elliptic curve arithmetic, and it is especially costly in the quantum setting. Our goal in this paper is to optimize quantum multiplication in the binary field. In the past, efforts to optimize quantum multiplication have centred on reducing the Toffoli gate count or qubits required. However, despite the fact that circuit depth is an important metric for indicating the performance of a quantum circuit, previous studies have lacked sufficient consideration for reducing circuit depth. Our approach to optimizing quantum multiplication differs from previous work in that we aim at reducing the Toffoli depth and full depth. To optimize quantum multiplication, we adopt the Karatsuba multiplication method which is based on the divide-and-conquer approach. In summary, we present an optimized quantum multiplication that has a Toffoli depth of one. Additionally, the full depth of the quantum circuit is also reduced thanks to our Toffoli depth optimization strategy. To demonstrate the effectiveness of our proposed method, we evaluate its performance using various metrics such as the qubit count, quantum gates, and circuit depth, as well as the qubits-depth product. These metrics provide insight into the resource requirements and complexity of the method. Our work achieves the lowest Toffoli depth, full depth, and the best trade-off performance for quantum multiplication. Further, our multiplication is more effective when not used in stand-alone cases. We show this effectiveness by using our multiplication to the Itoh–Tsujii algorithm-based inversion of

F (x^{8} + x^{4} + x^{3} + x + 1)

. Full article

► Show Figures

Figure 1

23 pages, 847 KiB

Open AccessArticle

APT Attack Detection Scheme Based on CK Sketch and DNS Traffic

by Defan Xue, Yaping Chi, Bing Wu and Lun Zhao

Sensors 2023, 23(4), 2217; https://doi.org/10.3390/s23042217 - 16 Feb 2023

Cited by 1 | Viewed by 2541

Abstract

In recent years, Advanced Persistent Threat (APT) attacks against sensors have emerged as a prominent security concern. Due to the low level of protection provided by sensors, APT attack organizations are able to develop intrusion schemes that allow them to infiltrate, attack, lurk, [...] Read more.

In recent years, Advanced Persistent Threat (APT) attacks against sensors have emerged as a prominent security concern. Due to the low level of protection provided by sensors, APT attack organizations are able to develop intrusion schemes that allow them to infiltrate, attack, lurk, spread, and steal information from the target over an extended period of time. Through extensive research on the APT attack process and current defense mechanisms, it has been found that analyzing Domain Name Server (DNS) traffic in the communication control phase is an effective way of detecting APT attacks. However, analyzing APT attacks based on traffic usually involves the detection of a vast amount of DNS traffic, and current data preprocessing methods do not scale down data effectively, leading to low detection efficiency. In previous work, most efforts have been focused on calculating the features of request messages or corresponding messages without considering the association between request messages and corresponding messages. To address these issues, we propose a sketch-based APT attack traffic detection scheme. The scheme leverages the sketch structure to count and compress network traffic, improving the efficiency of APT detection. Our work also analyzes the limitations of traditional sketches in network traffic and proposes an improved sketch scheme. In addition, we propose several effective features for detecting APT attacks. We validate and evaluate our solution using 1,088,280 DNS traffic from a lab network and APT suspicious traffic from netresec and contagio, using eight machine learning models. The experimental results show that for the ExtraTrees model, our solution has a processing time of 0.0638 s and an accuracy of 0.97920, reducing the processing time by approximately 50 times and improving detection accuracy by a small margin compared to a dataset without sketch processing. Full article

► Show Figures

Figure 1

2022

Jump to: 2024, 2023

30 pages, 7525 KiB

Open AccessArticle

An Implementation of Trust Chain Framework with Hierarchical Content Identifier Mechanism by Using Blockchain Technology

by Hsing-Chung Chen, Bambang Irawan, Pei-Yu Hsu, Jhih-Sheng Su, Chun-Wei (Jerry) Lin, Prayitno, Karisma Trinanda Putra, Cahya Damarjati, Chien-Erh Weng, Yao-Hsien Liang and Pi-Hsien Chang

Sensors 2022, 22(13), 4831; https://doi.org/10.3390/s22134831 - 26 Jun 2022

Cited by 6 | Viewed by 3527

Abstract

Advances in information technology (IT) and operation technology (OT) accelerate the development of manufacturing systems (MS) consisting of integrated circuits (ICs), modules, and systems, toward Industry 4.0. However, the existing MS does not support comprehensive identity forensics for the whole system, limiting its [...] Read more.

Advances in information technology (IT) and operation technology (OT) accelerate the development of manufacturing systems (MS) consisting of integrated circuits (ICs), modules, and systems, toward Industry 4.0. However, the existing MS does not support comprehensive identity forensics for the whole system, limiting its ability to adapt to equipment authentication difficulties. Furthermore, the development of trust imposed during their crosswise collaborations with suppliers and other manufacturers in the supply chain is poorly maintained. In this paper, a trust chain framework with a comprehensive identification mechanism is implemented for the designed MS system, which is based and created on the private blockchain in conjunction with decentralized database systems to boost the flexibility, traceability, and identification of the IC-module-system. Practical implementations are developed using a functional prototype. First, the decentralized application (DApp) and the smart contracts are proposed for constructing the new trust chain under the proposed comprehensive identification mechanism by using blockchain technology. In addition, the blockchain addresses of IC, module, and system are automatically registered to InterPlanetary File System (IPFS), individually. In addition, their corresponding hierarchical CID (content identifier) values are organized by using Merkle DAG (Directed Acyclic Graph), which is employed via the hierarchical content identifier mechanism (HCIDM) proposed in this paper. Based on insights obtained from this analysis, the trust chain based on HCIDM can be applied to any MS system, for example, this trust chain could be used to prevent the counterfeit modules and ICs employed in the monitoring system of a semiconductor factory environment. The evaluation results show that the proposed scheme could work in practice under the much lower costs, compared to the public blockchain, with a total cost of 0.002094 Ether. Finally, this research is developed an innovation trust chain mechanism that could be provided the system-level security for any MS toward Industrial 4.0 in order to meet the requirements of both manufacturing innovation and product innovation in Sustainable Development Goals (SDGs). Full article

► Show Figures

Figure 1

21 pages, 3888 KiB

Open AccessEditor’s ChoiceArticle

Effective Feature Selection Methods to Detect IoT DDoS Attack in 5G Core Network

by Ye-Eun Kim, Yea-Sul Kim and Hwankuk Kim

Sensors 2022, 22(10), 3819; https://doi.org/10.3390/s22103819 - 18 May 2022

Cited by 30 | Viewed by 5585

Abstract

The 5G networks aim to realize a massive Internet of Things (IoT) environment with low latency. IoT devices with weak security can cause Tbps-level Distributed Denial of Service (DDoS) attacks on 5G mobile networks. Therefore, interest in automatic network intrusion detection using machine [...] Read more.

The 5G networks aim to realize a massive Internet of Things (IoT) environment with low latency. IoT devices with weak security can cause Tbps-level Distributed Denial of Service (DDoS) attacks on 5G mobile networks. Therefore, interest in automatic network intrusion detection using machine learning (ML) technology in 5G networks is increasing. ML-based DDoS attack detection in a 5G environment should provide ultra-low latency. To this end, utilizing a feature-selection process that reduces computational complexity and improves performance by identifying features important for learning in large datasets is possible. Existing ML-based DDoS detection technology mostly focuses on DDoS detection learning models on the wired Internet. In addition, studies on feature engineering related to 5G traffic are relatively insufficient. Therefore, this study performed feature selection experiments to reduce the time complexity of detecting and analyzing large-capacity DDoS attacks in real time based on ML in a 5G core network environment. The results of the experiment showed that the performance was maintained and improved when the feature selection process was used. In particular, as the size of the dataset increased, the difference in time complexity increased rapidly. The experiments show that the real-time detection of large-scale DDoS attacks in 5G core networks is possible using the feature selection process. This demonstrates the importance of the feature selection process for removing noisy features before training and detection. As this study conducted a feature study to detect network traffic passing through the 5G core with low latency using ML, it is expected to contribute to improving the performance of the 5G network DDoS attack automation detection technology using AI technology. Full article

► Show Figures

Figure 1

11 pages, 2411 KiB

Open AccessArticle

A Universal Detection Method for Adversarial Examples and Fake Images

by Jiewei Lai, Yantong Huo, Ruitao Hou and Xianmin Wang

Sensors 2022, 22(9), 3445; https://doi.org/10.3390/s22093445 - 30 Apr 2022

Cited by 1 | Viewed by 2380

Abstract

Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable to adversarial examples that make the model’s predictions wrong due to some specific [...] Read more.

Deep-learning technologies have shown impressive performance on many tasks in recent years. However, there are multiple serious security risks when using deep-learning technologies. For examples, state-of-the-art deep-learning technologies are vulnerable to adversarial examples that make the model’s predictions wrong due to some specific subtle perturbation, and these technologies can be abused for the tampering with and forgery of multimedia, i.e., deep forgery. In this paper, we propose a universal detection framework for adversarial examples and fake images. We observe some differences in the distribution of model outputs for normal and adversarial examples (fake images) and train the detector to learn the differences. We perform extensive experiments on the CIFAR10 and CIFAR100 datasets. Experimental results show that the proposed framework has good feasibility and effectiveness in detecting adversarial examples or fake images. Moreover, the proposed framework has good generalizability for the different datasets and model structures. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Cryptography and Security in IoT and Sensor Networks

Share This Topical Collection

Editors

Topical Collection Information

Published Papers (14 papers)

2024

Jump to: 2023, 2022

2023

Jump to: 2024, 2022

2022

Jump to: 2024, 2023

Further Information

Guidelines

MDPI Initiatives

Follow MDPI