Journal of Cyber Security and Mobility

Feasibility of Using Seq-GAN Model in Vulnerability Detection of Industrial Control Protocols

2023-10-15T21:40:38+02:00

Continuous improvement of internet technology has driven the continuous progress and improvement of industrial control systems, and provided more support for security vulnerability detection in this field. Combining the GAN model, the detection model based on Seq-GAN in industrial control protocol vulnerabilities constructed in this article provides more options for further improving the security of industrial control systems, and can detect and analyse security vulnerabilities in industrial control protocols more efficiently and accurately. By comparing the performance of different models for security vulnerability detection, the Seq-GAN model has smaller prediction errors, can also obtain higher G-mean and F1-score values, and has sufficient reliability. At the same time, it can also improve the efficiency of vulnerability detection in industrial control systems, and can achieve better comprehensive detection performance. Therefore, the application of the Seq-GAN model in industrial control protocol vulnerability detection can provide more support for improving security detection in this field.

Construction and Analysis of QPSO-LSTM Model in Network Security Situation Prediction

2023-09-25T14:25:36+02:00

The continuous improvement of artificial intelligence technology has deepened its application in many fields and provided more support for predicting network security situations. QPSO-LSTM model based on LSTM neural network and fused with QPSO algorithm provides more options for improving network security situation prediction, further enhancing the effectiveness of network security situation prediction, and enabling more efficient and accurate prediction and analysis of network security situations. By comparing the applications of different types of algorithms in network security situation prediction, it was found that the QPSO-LSTM model has smaller prediction errors, can achieve higher prediction accuracy, and can also obtain higher F $_{1}$ -score and AUC values; the shorter identifying runtime also lays the foundation for improving the speed and efficiency of network security situation prediction. Therefore, in the field of network security situation prediction, the application of QPSO-LSTM model can provide more support for further improvement and improvement of security situation prediction performance in this field.

Construction and Analysis of Network Cloud Security Situation Awareness System Based on DBN-DE Algorithm

2023-12-04T19:59:48+01:00

With the wide application of cloud computing, network security has become the primary issue in cloud environment. This study focuses on constructing a system focusing on network cloud security situation awareness, and combines deep belief network with differential evolution algorithm to improve the perception and analysis capability of network cloud security. Differential evolution algorithm is used to optimize DBN weights and parameters to improve system performance and generalization ability. In the aspect of system performance evaluation, the effectiveness of the system is verified by a series of experiments. The experimental results show that the system based on DBN-DE has excellent performance in network attack detection and can quickly identify various potential threats. The system also has a low false alarm rate, which can reduce the frequency of administrator intervention, and improve the efficiency and reliability of network cloud security.

Optimization of Network Security Intelligent Early Warning System Based on Image Matching Technology of Partial Differential Equation

2023-11-22T19:56:20+01:00

In order to effectively avoid network information leakage and computer network paralysis, and improve the ability of computer network security early warning, it is necessary to design a computer network security intelligent early warning system based on network behavior. Security warning is considered as the second defense mechanism behind the firewall. It can monitor and warn the network without affecting the network performance, so as to provide real-time protection for external attacks, internal attacks and misoperations, and improve the network security. This paper designs an intelligent early warning system for network security based on partial differential equation image matching technology. The system adopts B/S development mode, and the server and browser are located in the campus network. Data fusion technology is used to assess network security, predict potential threats, and add new intrusion features to the feature database for subsequent use. In this paper, a target matching algorithm based on partial differential equation is proposed by using partial differential equation. The algorithm calculates the phase difference through the algebraic combination of orthogonal filter outputs. For scenes with continuous disparity changes, the error matching rate of this algorithm is lower than that of Michael Bleyer algorithm and vertical constraint algorithm. In general, the disparity map generated by this algorithm has high matching accuracy. The results show that the distribution of alarm information is reasonable and in line with the actual situation.

A Study of An Image Encryption Model Based on Tent-Ushiki Chaotic Fusion

2023-11-08T16:41:51+01:00

Aiming at the shortcomings of current image encryption, such as simple structure, few parameters and small key space, we propose the Tent-Ushiki chaotic mapping image encryption method based on the improved firefly optimization algorithm. First, a chaotic mapping model based on the fusion of Tent and Ushiki is proposed. Second, for the lack of parameter optimization in chaotic models in general, we introduce the firefly optimization algorithm and optimize the algorithm for the shortcomings in terms of the adaptive step size, the adjustment factor and the inertia weights. Finally, the improved firefly algorithm is used for the fusion of the chaotic parameters of Tent and Ushiki. In the simulation experiments, this paper’s algorithm performs well in the statistical analysis and adjacent element correlation of the classical image test and significantly outperforms the comparative algorithms in terms of information entropy and anti-attack, which demonstrates that the algorithm is able to optimize the image encryption effect better.

Attribute Based Signature Encryption Scheme Based on Cloud Computing in Medical Social Networks

2023-12-12T23:35:34+01:00

The emergence of mobile medical social networks has provided great convenience for patients to communicate with each other about their medical conditions, promoting efficient and high-quality communication and exchange among patients. However, at the same time, it has also raised issues of confidentiality and privacy of patient data. In response to this issue, this article proposes a cloud-based attribute-based signature encryption scheme that can effectively protect the privacy of patient data. The patient encrypts their medical information and uploads it to the cloud server. When the data user wants to access the patient’s information, the cloud server helps the data user partially decrypt and verify the integrity of the data, which to some extent reduces the computational workload of the data user. Meanwhile, under the random oracle model, it has been proven that the scheme satisfies the unforgeability under selective message attacks, indistinguishability under selective cipher text attacks, and attribute privacy security. Theoretical analysis and numerical simulation experiments show that this scheme has higher efficiency than existing schemes in the signing and decryption stages.

Enhancement of Tiny Encryption Algorithm for Resource-Constrained WSNs Using Four Connected Additive Fibonacci Generators

2023-10-26T00:48:03+02:00

The usage of wireless sensor networks (WSN) is widespread in industries where data security is crucial. Due to the energy and computational limits of WSN, the cryptographic protocols designed for it must be as computationally cheap as feasible. The components of these protocols, such as the random number generator, are subject to the same constraints. For such resource-constrained devices, several lightweight encryption techniques have been created. One of the most efficient lightweight ciphers is Tiny Encryption Algorithm (TEA). TEA uses a few lines of source code that are based on Feistel. It is however susceptible to attacks utilizing equivalent and related key attacks. In order to address TEA’s key vulnerabilities, a modification is suggested in this paper that focuses on key creation. Four connected Additive Fibonacci Generators (AFGs) make up the structure, which addresses the security vulnerability by using a unique key each round. Performance evaluation was assessed using three statistical tests: avalanche effect, randomness analysis, and completeness testing. Through experimental results, ATEA outperforms TEA by an average of 51.68 % to 47.51 % for the avalanche effect, and 51.95 % to 48.36 % for the completeness test, and satisfies all the NIST requirements. Results of advanced security measurements indicate that, ATEA can be used to secure WSN devices.

On the Security of Key-Aggregate Searchable Encryption

2024-01-25T09:07:03+01:00

The sharing of encrypted data in cloud computing is an essential functionality with countless applications in our everyday life. However, the issue of how to securely, efficiently and flexibly share encrypted data in multi-user settings has not been well solved. As a promising and elegant technique, the key-aggregate searchable encryption (KASE) scheme can efficiently support selective sharing of a large number of documents with a set of users using only a single, constant-size authorization key (i.e., the aggregated key). However, by conducting cryptanalysis on existing KASE schemes, we classify the attack methods into two types: offline keyword guessing attacks and authorization abuse. For the former attacks, we first employ the known keyword guessing attack methods to cryptanalyze several existing KASE schemes. Furthermore, we propose two novel keyword guessing attack methods, namely (1) Keyword guessing attack by modifying ciphertext and (2) Keyword guessing attack by constructing verification equation. For the latter attacks, we first utilized the known authorization abuse attack methods to cryptanalyze several existing KASE schemes. Furthermore, we develop a novel attack method in which the attacker can independently upgrade their own authorization and gain enhanced search privileges without colluding with multiple authorized users.

Internet of Things Security Design Based on Blockchain and Identity Re-encryption

2023-12-22T12:34:58+01:00

With the development of IoT technology, IoT devices have penetrated various fields, such as smart homes, industrial automation, healthcare, etc. However, the security issues of IoT devices have always troubled people. Attackers can use various means to attack IoT devices, such as stealing data, tampering with programs, malware infection, etc. These attack methods will bring great losses to users. In response to the above issues, this study uses proxy re-encryption technology to transform data collected by IoT devices into ciphertext. Then, it stores the encrypted IoT data on the blockchain. The combination of blockchain and proxy re-encryption technologies offers a method for the secure sharing of IoT data. The experimental results show that whether the algorithm encrypts a small or large amount of data, the encryption time is relatively short, and the time consumption does not exceed 15 ms. When encrypting 8196 bytes of data, its encryption time is 50% lower than the Attribute-Based Encryption (ABE) algorithm. The proposed IoT data security sharing method has the advantages of high security, fast encryption speed, and good stability, which helps to improve the security performance of the IoT and provides a new approach to IoT security.

Robustness and Collision-Resistance of PhotoDNA

2024-01-04T14:51:52+01:00

PhotoDNA is a widely utilized hash designed to counteract Child Sexual Abuse Material (CSAM). However, there has been a scarcity of detailed information regarding its performance. In this paper, we present a comprehensive analysis of its robustness and susceptibility to false positives, along with fundamental insights into its structure. Our findings reveal its resilience to common image processing techniques like lossy compression. Conversely, its robustness is limited when confronted with cropping. Additionally, we propose recommendations for enhancing the algorithm or optimizing its application. This work is an extension on our paper [21].