نشریه مهندسی برق و مهندسی کامپیوتر ایران
سال بیست و چهارم شماره 4 (پیاپی 83، زمستان 1402)

Blockchain technology eliminates the need for a central authority. This system consists of a distributed ledger with a chain of blocks that records every network transaction. This ledger is replicated by every node in the network. We require a mechanism that provides consensus for the entire network, known as "consensus algorithm," in order for the state of this ledger to be the same for all nodes of the network at any given time. In this work, we will suggest a novel consensus algorithm that protects the blockchain platform from four common attacks. These attacks include the Sybil, Denial of Service, 51%, and Eclipse attacks. Due to its multiple control parameters, generic and all-purpose character, immunity to different attacks, and acceptable execution speed, our suggested algorithm can be used to build secure blockchain-based systems in a variety of applications.

The rise of Software-Defined Networking (SDN) has revolutionized network management, offering greater flexibility and programmability. However, ensuring the accuracy of packet forwarding remains paramount for maintaining network reliability and security in SDN environments. Unlike traditional IP networks, SDN separates the control plane from the data plane, creating new challenges for securing data transmission. Existing verification methods designed for IP networks often cannot be directly applied to SDN due to this architectural difference. To address the limitations of existing verification methods in SDN networks, new approaches are necessary. This research proposes a novel parallel method for verifying packet forwarding, building upon concepts from DYNAPFV. The proposed approach aims to overcome specific limitations of existing methods (including DYNAPFV), such as scalability issues, slow verification times. Simulations demonstrate significant improvements compared to DYNAPFV. The proposed parallel method achieves a 92% reduction in time required to identify malicious nodes within the network. The results also reveal a trade-off between security and verification time. As the probability of packet integrity confirmation increases from 0.8 to 0.99, system security strengthens, but the time to detect malicious switches also increases.

Nowadays, the Internet of Things (IoT) has become the focus of security attacks due to the limitation of processing resources, heterogeneity, energy limitation in objects, and the lack of a single standard for implementing security mechanisms. In this article, a solution will be presented for the problem of security resources allocating to deal with attacks in the Internet of Things. Security Resource Allocation (SRA) problem in the IoT networks refers to the placement of the security resources in the IoT infrastructure. To solve this problem, it is mandatory to consider the dynamic nature of the communication environments and the uncertainty of the attackers' actions. In the traditional approaches for solving the SRA, the attacker works over based on his assumptions about the system conditions. Meanwhile, the defender collects the system's information with prior knowledge of the attacker's behavior and the targeted nodes. Unlike the mentioned traditional approaches, this research has adopted a realistic approach for the Dynamic Security Resources Allocation in the IoT to battle attackers with unknown behavior. In the stated problem, since there is a need to decide on deploying several security resources during the learning periods, the state space of the strategies is expressed in the combinatorial form. Also, the SRAIoT problem is defined as a combinatorial-adversarial multi-armed bandit problem. Since switching in the security resources has a high cost, in real scenarios, this cost is included in the utility function of the problem. Thus, the proposed framework considers the switching cost and the earned reward. The simulation results show a faster convergence of the weak regret criterion of the proposed algorithms than the basic combinatorial algorithm. In addition, in order to simulate the IoT network in a realistic context, the attack scenario has been simulated using the Cooja simulator.

The Social Internet of Things (SIoT) network is the result of the union of the Social Network and the Internet of Things network; wherein, each object tries to use the services provided by its friends. In this network, to find the right friend in order to use the right service is demanding. Great number of objects' friends, in classical algorithms, causes increasing the computational time and load of network navigation to find the right service with the help of friendly objects. In this article, in order to reduce the computational load and network navigation, it is proposed, firstly, to select the appropriate object friend from a heuristic approach; secondly, to use an adapted binary cuckoo optimization algorithm (AB-COA) which tries to select the appropriate friendly object to receive the service according to the maximum response capacity of each friendly object, and finally, adopting the Adamic-Adar local index (AA) with the interest degree centrality criterion so that it represents the characteristics of the common neighbors of the objects are involved in the friend selection. Finally, by executing the proposed algorithm on the Web-Stanford dataset, an average of 4.8 steps was obtained for reaching a service in the network, indicating the superiority of this algorithm over other algorithms.

 In the era of big data, automatic data analysis techniques such as data mining have been widely used for decision-making and have become very effective. Among data mining techniques, classification is a common method for decision making and prediction. Classification algorithms usually work well on balanced datasets. However, one of the challenges of the classification algorithms is how to correctly predicting the label of new samples based on learning on imbalanced datasets. In this type of dataset, the heterogeneous distribution of the data in different classes causes examples of the minority class to be ignored in the learning process, while this class is more important in some prediction problems. To deal with this issue, in this paper, an efficient method for balancing the imbalanced dataset is presented, which improves the accuracy of the machine learning algorithms to correct prediction of the class label of new samples. According to the evaluations, the proposed method has a better performance compared to other methods based on two common criteria in evaluating the classification of imbalanced datasets, namely "Balanced Accuracy" and "Specificity".

Today, social networks play a crucial role in disseminating information worldwide. Twitter is one of the most popular social networks, with 500 million tweets sent on a daily basis. The popularity of this network among users has led spammers to exploit it for distributing spam posts. This paper employs a combination of machine learning methods to identify spam at the tweet level. The proposed method utilizes a feature extraction framework in two stages. In the first stage, Stacked Autoencoder is used for feature extraction, and in the second stage, the extracted features from the last layer of Stacked Autoencoder are fed into the softmax layer for prediction. The proposed method is compared and evaluated against some popular methods on the Twitter Spam Detection corpus using accuracy, precision, recall, and F1-score metrics. The research results indicate that the proposed method achieves a detection of 78.1%. Overall, the proposed method, using the majority voting approach with a hard selection in ensemble learning, outperforms CNN, LSTM, and SCCL methods in identifying spam tweets with higher accuracy.

In any adiabatic quantum computation, there exist an initial state that must be used in the corresponding quantum algorithm. In this paper, the relation between an initial state and allowed energy level of an implemented generalized Deutsch’s algorithm is investigated. To study the generalized Deutsch’s algorithm, a compacted form for the output states of the algorithm is obtained. It has been shown that one can prepare the initial states in such a way that control the minimum of energy. By using numerical methods, the minimum values of allowed energy levels for the initial state are obtained. Also, to study the dynamics of the system is chosen. The corresponding Hamiltonian for the algorithm is obtained and it has been shown that one of the energy levels describes a binding state.