Abstract Segmentation is crucial in diagnosing retinal diseases by accurately identifiying retinal vessels. This paper addresses the complexity of segmenting retinal vessels, highlighting the need for precise analysis of blood vessel structures. Despite the progress made by convolutional neural networsks (CNNs) in image segmentation, their limitations in capturing the global structure of retinal vsessels and maintaining segmentation continuity present challenges. To tackle these issues, our proposed network integrates graph convolutional networks (GCNs) and attention mechansims. This allows the model to consider pixel relationships and learn vessel graphical structures, significantly improving segmentation accuracy. Additionally, the attentional feature fusion module, including pixel‐wise and channel‐wise attention mechansims within the U‐Net architecture, refines the model's focus on relevant features. This paper emphasizes the importance of continuty preservation, ensuring an accurate representation of pixel‐level information and structural details during sefmentation. Therefore, our method performs as an effective solution to overcome challenges in retinal vessel segmentation. The proposed method outperformed the state‐of‐the‐art approaches on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (Structed Analysis of the Retina) datasets with accuracies of 0.12% and 0.14%, respecttively. Importantly, our proposed approach excelled in delineating slender and diminutive blood vessels, crucial for diagnosing vascular‐related diseases. Implementation is accessible on https://github.com/CVLab‐SHUT/VGA‐Net .

Abstract A recent approach to image steganography is to use deep learning. Mainly, convolutional neural networks can extract complex features and use them as patterns to combine hidden messages and images. Also, by using generative adversarial networks, it is possible to generate realistic and high‐quality stego images without any noticeable artifacts. Previous methods suffered from challenges such as simple architecture, low network accuracy, imbalance between capacity and transparency, vanishing gradients, and low capacity. This study introduces a steganography framework named VidaGAN that utilizes deep learning techniques. The network being proposed is made up of three components: an encoder, a decoder, and a critic, and introduces a novel architecture and several innovations to address some of the unresolved challenges mentioned above. This study introduces a novel method for embedding any type of binary data into images using generative adversarial networks, enabling us to enhance the visual appeal of images generated by the specified model. This neural network called VarIable aDAptive GAN (VidaGAN) achieved state‐of‐the‐art status by reaching a hiding capacity of 3.9 bits per pixel in the DIV2K dataset. Furthermore, examination by the StegExpose steganalysis tool shows an AUC of 0.6, a suitable threshold for transparency.

Due to the increasing sophistication of web attacks, Web Application Firewalls (WAFs) have to be tested and updated regularly to resist the relentless flow of web attacks. In practice, using a brute-force attack to discover vulnerabilities is infeasible due to the wide variety of attack patterns. Thus, various black-box testing techniques have been proposed in the literature. However, these techniques suffer from low efficiency. This article presents Reinforcement-Learning-Driven and Adaptive Testing (RAT), an automated black-box testing strategy to discover injection vulnerabilities in WAFs. In particular, we focus on SQL injection and Cross-site Scripting, which have been among the top ten vulnerabilities over the past decade. More specifically,RATclusters similar attack samples together. It then utilizes a reinforcement learning technique combined with a novel adaptive search algorithm to discover almost all bypassing attack patterns efficiently. We compareRATwith three state-of-the-art me&thods considering their objectives. The experiments show thatRATperforms 33.53 and 63.16 percent on average better than its counterparts in discovering the most possible bypassing payloads and reducing the number of attempts before finding the first bypassing payload when testing well-configured WAFs, respectively.

The next generation of wireless networks including Five and Six Generations ( 5 G and 6 G ) can provide very high data rates as a demand for the Internet of Everything (IoE) system which connects millions of people and billions of machines. To reach such a high data rate, the wireless networks should work at high enough frequencies, such as millimeter and THz bands, which in turn suffer from a large attenuation and acute multipath fading. The idea of coating any objects in the environment with Software-Defined Metasurfaces (SDMs) was presented to control these effects by managing the electromagnetic properties of the environment. Since the programmable environment can be changed during the communication, for example, a sudden obstacle appears, this management should be adaptive. This paper presents the use of a reinforcement learning (RL) algorithm for dynamically configuring such an environment. In other words, when a change happens in the environment, for example, an obstacle blocks some EM waves, the agent receives a large punishment, and therefore a new action is selected. In our model, the transmitted electromagnetic waves and the tiles are considered as the agents and states, respectively. Moreover, the actions of each tile include absorbing or reflecting the impinging waves in a specific direction. We utilize the Q-learning technique to establish proper wireless links between the users and the access point (AP) by controlling the state of the tiles in an environment covered by the SDMs. Evaluation of the proposed model for different scenarios, including emerging sudden obstacles, indicates its potential to provide a proper signal level for all the users and improve the average received power up to 12 % in comparison with the related works.

LSB matching revisited is an LSB-based approach for image steganography. This method is a type of coding to increase the capacity of steganography. In this method, two bits of the secret message are hidden in two pixels with only one change. But this method provides no idea for hiding a message with a large number of bits. In other words, this method works only for n = 2 , where n is the number of bits in a block of the secret message. In this paper, we propose an improved version of the LSB matching revisited approach, which works for n > 2 . The proposed scheme contains two phases including embedding and extracting the message. In the embedding phase, we first convert the secret message into a bit-stream, and then the bit-stream is divided into a set of blocks including n bits in each block. Then we choose 2 n − 1 pixels for hiding such n bits of the secret message. In the next step, we choose the operations needed to generate such a message. Finally, we perform the obtained operations over the coefficients to hide the secret message. The proposed approach needs fewer changes than LSB MR when n > 2 . The capacity of the proposed approach is 2 n − 1 / 2 n − 1 − 1 × 100 % higher than the F5 method where this value for n > 2 is bigger than 75%. For example, the capacity of our scheme is 75% higher than the capacity of F5 for n = 3 . The proposed method can be used in the first step of every steganography method to reduce the change in the stego image. Therefore, this method is a new coding method for steganography. Our experimental results using steganalysis show that using our method provides around 10% higher detection error for SRNet over two steganography schemes.

In GSM, the network is not authenticated which allows for man-in-the-middle (MITM) attacks. Attackers can track traffic and trace users of cellular networks by creating a rogue base transceiver station (BTS). Such a defect in addition to the need for backward compatibility of mobile networks makes all GSM, UMTS, and LTE networks susceptible to MITMs. These attacks are conducted using IMSI-Catchers (ICs). Most of the solutions proposed for detecting ICs in the literature are based on using specific mobile devices with root access. Also, they cannot identify ICs to which users are not connected. In this paper, we propose an approach called YAICD for detecting ICs in the GSM network. YAICD consists of a sensor that can be installed on Android mobile devices. It detects ICs by extracting 15 parameters from signals received from BTSs. We also established a lab-scale testbed to evaluate YAICD for various detection parameters and for comparing it against existing solutions in the literature. The experimental results show that YAICD not only successfully detects ICs using the parameters but also identifies ICs to which users are not yet connected to the network.

Optical character recognition, known as OCR, has been widely used due to high demand of different technologies. Currently, most existing OCR systems have been focused on Latin languages. In recent studies, OCR systems for non‐Latin texts involving cursive style have also been introduced despite posing some challenges. In this study, the authors propose an OCR system based on long short‐term memory neural networks for the Persian language. The authors also investigate the effects of variations of parameters, involved in this approach. The proposed OCR system solves false recognition of sub‐word ‘LA’ and ‘LA’. Moreover, the authors present a preprocessing algorithm to remove ‘justification’ using image processing. A new comprehensive collated data set is introduced, comprising five million images with eight popular Persian fonts and in ten various font sizes. The proposed evaluations show that the accuracy of the proposed OCR is increased by 2%, compared to the existing Persian OCR system. The experimental results indicated that the proposed system has average accuracy of 99.69% at the letter level. The proposed system has an accuracy of 98.1% for ‘zero‐width non‐breaking space’ and 98.64% for ‘LA’ at the word level.

Brain–computer interface (BCI) is a powerful system for communicating between the brain and outside world. Traditional BCI systems work based on electroencephalogram (EEG) signals only. Recently, researchers have used a combination of EEG signals with other signals to improve the performance of BCI systems. Among these signals, the combination of EEG with functional near‐infrared spectroscopy (fNIRS) has achieved favourable results. In most studies, only EEGs or fNIRs have been considered as chain‐like sequences, and do not consider complex correlations between adjacent signals, neither in time nor channel location. In this study, a deep neural network model has been introduced to identify the exact objectives of the human brain by introducing temporal and spatial features. The proposed model incorporates the spatial relationship between EEG and fNIRS signals. This could be implemented by transforming the sequences of these chain‐like signals into hierarchical three‐rank tensors. The tests show that the proposed model has a precision of 99.6%.

Verifiable secret sharing (VSS) is one of the basic problems in the theory of distributed cryptography and has an important role in secure multiparty computation. In this case, it is tried to share a confidential data as secret, between multiple nodes in a distributed system, in the presence of an active adversary that can destroy some nodes, such that the secret can be reconstructed with the participation of certain size of honest nodes. A dynamic adversary can change its corrupted nodes among the protocol. So far, there is not a formal definition and there are no protocols of dynamic adversaries in VSS context. Also, another important question is, would there exist a protocol to share a secret with a static adversary with at most 1 broadcast round? In this paper, we provide a formal definition of the dynamic adversary. The simulation results prove the efficiency of the proposed protocol in terms of the runtime, the memory usage, and the number of message exchanges. We show that the change period of the dynamic adversary could not happen in less than 4 rounds in order to have a perfectly secure VSS, and then we establish a protocol to deal with this type of adversary. Also, we prove that the lower bound of broadcast complexity for the static adversary is (2,0)-broadcast rounds.

Data aggregation in Wireless Sensor Networks (WSNs) can effectively reduce communication overheads and reduce the energy consumption of sensor nodes. A WSN needs to be not only energy efficient but also secure. Various attacks may make data aggregation unsecure. We investigate the reliable and secure end-to-end data aggregation problem considering selective forwarding attacks and modification attacks in homogeneous WSNs, and propose two data aggregation approaches. Our approaches, namely Sign-Share and Sham-Share, use secret sharing and signatures to allow aggregators to aggregate the data without understanding the contents of messages and the base station to verify the aggregated data and retrieve the raw data from the aggregated data. To the best of our knowledge, this is the first lightweight en-routing malicious node detection in concealed data aggregation. We have performed an extensive simulation to compare our approaches and the two state-of-the-art approaches PIP and RCDA-HOMO. The simulation results show that both Sign-Share and Sham-Share consume a reasonable amount of time in processing and aggregating the data. The simulation results show that our first approach achieved an average network lifetime of 102.33% over PIP and average aggregation energy consumption of 74.93%. In addition, it achieved an average aggregation processing time and sensor data processing time of 95.4% and 90.34% over PIP and 98.7% and 92.07% over RCDA-HOMO, respectively, and it achieved an average network delay of 71.95% over PIP. Although RCDA-HOMO is completely a different technique, a comparison was performed to measure the computational overhead.

Online rating systems are widely accepted as means for quality assessment on the web and users increasingly rely on these systems when deciding to purchase an item online. This makes such rating systems frequent targets of attempted manipulation by posting unfair rating scores. Therefore, providing useful, realistic rating scores as well as detecting unfair behavior are both of very high importance. Existing solutions are mostly majority based, also employing temporal analysis and clustering techniques. However, they are still vulnerable to unfair ratings. They also ignore distances between options, the provenance of information, and different dimensions of cast rating scores while computing aggregate rating scores and trustworthiness of users. In this article, we propose a robust iterative algorithm which leverages information in the profile of users and provenance of information, and which takes into account the distance between options to provide both more robust and informative rating scores for items and trustworthiness of users. We also prove convergence of iterative ranking algorithms under very general assumptions, which are satisfied by the algorithm proposed in this article. We have implemented and tested our rating method using both simulated data as well as four real-world datasets from various applications of reputation systems. The experimental results demonstrate that our model provides realistic rating scores even in the presence of a massive amount of unfair ratings and outperforms the well-known ranking algorithms.

Outsourcing data to the cloud for computation and storage has been on the rise in recent years. In this paper we investigate the problem of supporting write operation on the outsourced data for clients using mobile devices. We consider the Ciphertext-Policy Attribute-based Encryption (CP-ABE) scheme as it is well suited to support access control in outsourced cloud environments. One shortcoming of CP-ABE is that users can modify the access policy specified by the data owner if write operations are incorporated in the scheme. We propose a protocol for collaborative processing of outsourced data that enables the authorized users to perform write operation without being able to alter the access policy specified by the data owner. Our scheme is accompanied with a light weight signature scheme and simple, inexpensive user revocation mechanism to make it suitable for processing on resource-constrained mobile devices. The implementation and detailed performance analysis of the scheme indicate the suitability of the proposed scheme for real mobile applications. Moreover, the security analysis demonstrates that the security properties of the system are not compromised.

Trust and reputation systems are widely employed in WSNs to help decision making processes by assessing trustworthiness of sensor nodes in a data aggregation process. However, in unattended and hostile environments, more sophisticated malicious attacks, such as collusion attacks, can distort the computed trust scores and lead to low quality or deceptive service as well as undermine the aggregation results. In this paper we propose a novel, local, collaborative-based trust framework for WSNs that is based on the concept of credibility propagation which we introduce. In our approach, trustworthiness of a sensor node depends on the amount of credibility that such a node receives from other nodes. In the process we also obtain an estimates of sensors' variances which allows us to estimate the true value of the signal using the Maximum Likelihood Estimation. Extensive experiments using both real-world and synthetic datasets demonstrate the efficiency and effectiveness of our approach.

Outsourcing data to the cloud for computation and storage has been on rise in recent years. In this paper we investigate the problem of supporting write operation on the outsourced data for clients using mobile devices. We consider the Attribute-based Encryption (ABE) scheme as it is well suited to support access control in outsourced cloud environment. Currently there is a gap in the literature on providing write access on the data encrypted with ABE. Moreover, since ABE is computationally expensive, it imposes processing burden on resource constrained mobile devices. Our work has two fold advantages. Firstly, we extend the single authority Ciphertext-Policy Attribute-based Encryption (CP-ABE) scheme to support write operations. Secondly, in achieving this goal, we move some of the expensive computations to a manager and remote cloud server by exploiting their high-end computational power. Our security analysis demonstrates that the security properties of system are not compromised.

Due to limited computational power and energy resources, aggregation of data from multiple sensor nodes done at the aggregating node is usually accomplished by simple methods such as averaging. However such aggregation is known to be highly vulnerable to node compromising attacks. Since WSN are usually unattended and without tamper resistant hardware, they are highly susceptible to such attacks. Thus, ascertaining trustworthiness of data and reputation of sensor nodes is crucial for WSN. As the performance of very low power processors dramatically improves, future aggregator nodes will be capable of performing more sophisticated data aggregation algorithms, thus making WSN less vulnerable. Iterative filtering algorithms hold great promise for such a purpose. Such algorithms simultaneously aggregate data from multiple sources and provide trust assessment of these sources, usually in a form of corresponding weight factors assigned to data provided by each source. In this paper we demonstrate that several existing iterative filtering algorithms, while significantly more robust against collusion attacks than the simple averaging methods, are nevertheless susceptive to a novel sophisticated collusion attack we introduce. To address this security issue, we propose an improvement for iterative filtering techniques by providing an initial approximation for such algorithms which makes them not only collusion robust, but also more accurate and faster converging.

Detection of high risk hosts and flows continues to be a significant problem in security monitoring of high throughput networks. A comprehensive risk assessment method should consider the risk propagation among risky hosts and flows. In this paper, this is achieved by introducing two novel concepts. First, an interdependency relationship among the risk scores of a network flow and its source and destination hosts. On the one hand, the risk score of a host depends on risky flows initiated by or terminated at the host. On the other hand, the risk score of a flow depends on the risk scores of its source and destination hosts. Second, which we call flow provenance, represents risk propagation among network flows which considers the likelihood that a particular flow is caused by the other flows. Based on these two concepts, we develop an iterative algorithm for computing the risk score of hosts and network flows. We give a rigorous proof that our algorithm rapidly converges to unique risk estimates, and provide its extensive empirical evaluation using two real-world data sets. Our evaluation shows that our method is effective in detecting high risk hosts and flows and is sufficiently efficient to be deployed in the high throughput networks.

Detection of high risk network flows and high risk hosts is becoming ever more important and more challenging. In order to selectively apply deep packet inspection (DPI) one has to isolate in real time high risk network activities within a huge number of monitored network flows. To help address this problem, we propose an iterative methodology for a simultaneous assessment of risk scores for both hosts and network flows. The proposed approach measures the risk scores of hosts and flows in an interdependent manner; thus, the risk score of a flow influences the risk score of its source and destination hosts, and also the risk score of a host is evaluated by taking into account the risk scores of flows initiated by or terminated at the host. Our experimental results show that such an approach not only effective in detecting high risk hosts and flows but, when deployed in high throughput networks, is also more efficient than PageRank based algorithms.

Discovering high risk network flows and hosts in a high throughput network is a challenging task of network monitoring. Emerging complicated attack scenarios such as DDoS attacks increase the complexity of tracking malicious and high risk network activities within a huge number of monitored network flows. To address this problem, we propose an iterative framework for assessing risk scores for hosts and network flows. To obtain risk scores of flows, we take into account two properties, flow attributes and flow provenance. Also, our iterative risk assessment measures the risk scores of hosts and flows based on an interdependency property where the risk score of a flow influences the risk of its source and destination hosts, and the risk score of a host is evaluated by risk scores of flows initiated by or terminated at the host. Moreover, the update mechanism in our framework allows flows to keep streaming into the system while our risk assessment method performs an online monitoring task. The experimental results show that our approach is effective in detecting high risk hosts and flows as well as sufficiently efficient to be deployed in high throughput networks compared to other algorithms.

In this paper we introduce a novel sophisticated collusion attack scenario against a number of existing iterative filtering algorithms. To address this security issue, we propose an improvement for iterative filtering techniques by providing an initial approximation for such algorithms which makes them not only collusion robust, but also more accurate and faster converging.