Biblio

In today’s digital world, Mobile SMS (short message service) communication has almost become a part of every human life. Meanwhile each mobile user suffers from the harass of Spam SMS. These Spam SMS constitute veritable nuisance to mobile subscribers. Though hackers or spammers try to intrude in mobile computing devices, SMS support for mobile devices become more vulnerable as attacker tries to intrude into the system by sending unsolicited messages. An attacker can gain remote access over mobile devices. We propose a novel approach that can analyze message content and find features using the TF-IDF techniques to efficiently detect Spam Messages and Ham messages using different Machine Learning Classifiers. The Classifiers going to use in proposed work can be measured with the help of metrics such as Accuracy, Precision and Recall. In our proposed approach accuracy rate will be increased by using the Voting Classifier.

In this paper, we established a unified deep learning-based spam filtering method. The proposed method uses the message byte-histograms as a unified representation for all message types (text, images, or any other format). A deep convolutional neural network (CNN) is used to extract high-level features from this representation. A fully connected neural network is used to perform the classification using the extracted CNN features. We validate our method using several open-source text-based and image-based spam datasets.We obtained an accuracy higher than 94% on all datasets.

The volume of SMS messages sent on a daily basis globally has continued to grow significantly over the past years. Hence, mobile phones are becoming increasingly vulnerable to SMS spam messages, thereby exposing users to the risk of fraud and theft of personal data. Filtering of messages to detect and eliminate SMS spam is now a critical functionality for which different types of machine learning approaches are still being explored. In this paper, we propose a system for detecting SMS spam using a semi-supervised novelty detection approach based on one class SVM classifier. The system is built as an anomaly detector that learns only from normal SMS messages thus enabling detection models to be implemented in the absence of labelled SMS spam training examples. We evaluated our proposed system using a benchmark dataset consisting of 747 SMS spam and 4827 non-spam messages. The results show that our proposed method out-performed the traditional supervised machine learning approaches based on binary, frequency or TF-IDF bag-of-words. The overall accuracy was 98% with 100% SMS spam detection rate and only around 3% false positive rate.

Digital communication platforms, such as Gmail and Yahoo, are become essential in our professional and personal lives. In addition to the low cost of e-mails, they are fast. Despite the advantages of these tools, spammers try to send unsolicited e-mail, known as spam, daily. Recently, image spam, a new type of spam e-mail, is developed by spammers in order to avoid detection based on text-based spam filtering systems. Image spam contains more complex information as compared to text spam. For this reason, the detection of image spam is still a challenging task for researchers. Most of the developed image spam filtering systems are based on hand-crafted features and machine learning techniques, which are time-consuming and less efficient. In addition, these systems do not focus on the important features, which can have an impact on the detection process. In this paper, we apply the convolutional block attention module (CBAM) model in order to address the problem of image spam. The experiments are conducted on the available dataset, called image spam hunter (ISH). The results obtained are then compared, using the CBAM model, to other existing state-of-the-art methods. The results obtained have demonstrated that the convolutional block attention module (CBAM) is efficient for image spam detection.

The new architecture of transformer networks proposed in the work can be used to create an intelligent chat bot that can learn the process of communication and immediately model responses based on what has been said. The essence of the new mechanism is to divide the information flow into two branches containing the history of the dialogue with different levels of granularity. Such a mechanism makes it possible to build and develop the personality of a dialogue agent in the process of dialogue, that is, to accurately imitate the natural behavior of a person. This gives the interlocutor (client) the feeling of talking to a real person. In addition, making modifications to the structure of such a network makes it possible to identify a likely attack using social engineering methods. The results obtained after training the created system showed the fundamental possibility of using a neural network of a new architecture to generate responses close to natural ones. Possible options for using such neural network dialogue agents in various fields, and, in particular, in information security systems, are considered. Possible options for using such neural network dialogue agents in various fields, and, in particular, in information security systems, are considered. The new technology can be used in social engineering attack detection systems, which is a big problem at present. The novelty and prospects of the proposed architecture of the neural network also lies in the possibility of creating on its basis dialogue systems with a high level of biological plausibility.

This paper examines audio-based social networking platforms and how their environments can affect the persistence of fake news and mis/disinformation in the whole information ecosystem. This is performed through an exploration of their features and how they compare to that of general-purpose multimodal platforms. A case study on Spotify and its recent issue on free speech and misinformation is the application area of this paper. As a supplementary, a demographic analysis of the current statistics of podcast streamers is outlined to give an overview of the target audience of possible deception attacks in the future. As for the conclusion, this paper confers a recommendation to policymakers and experts in preparing for future mis-affordance of the features in social environments that may unintentionally give the agents of mis/disinformation prowess to create and sow discord and deception.

This paper offers a comparative vector assessment of DDoS and disinformation attacks. The assessed dimensions are as follows: (1) the threat agent, (2) attack vector, (3) target, (4) impact, and (5) defense. The results revealed that disinformation attacks, anchoring on astroturfs, resemble DDoS’s zombie computers in their method of amplification. Although DDoS affects several layers of the OSI model, disinformation attacks exclusively affect the application layer. Furthermore, even though their payloads and objectives are different, their vector paths and network designs are very similar. This paper, as its conclusion, strongly recommends the classification of disinformation as an actual cybersecurity threat to eliminate the inconsistencies in policies in social networking platforms. The intended target audiences of this paper are IT and cybersecurity experts, computer and information scientists, policymakers, legal and judicial scholars, and other professionals seeking references on this matter.

Wireless Sensor Networks (WSN) have assisted applications of multi-agent system. Abundant sensor nodes, densely distributed around a base station (BS), collect data and transmit to BS node for data analysis. The concept of cluster has been emerged as the efficient communication structure in resource-constrained environment. However, the security still remains a major concern due to the vulnerability of sensor nodes. In this paper, we propose a percolation-based secure routing protocol. We leverage the trust score composed of three indexes to select cluster heads (CH) for unevenly distributed clusters. By considering the reliability, centrality and stability, legitimate nodes with social trust and adequate energy are chosen to provide relay service. Moreover, we design a multi-path inter-cluster routing protocol to construct CH chains for directed inter-cluster data transmission based on the percolation. And the measurement of transit score for on-path CH nodes contributes to load balancing and security. Our simulation results show that our protocol is able to guarantee the security to improve the delivery ratio and packets delay.

The ongoing COVID-19 virus pandemic has resulted in a global tragedy due to its lethal spread. The population's vulnerability grows as a result of a lack of effective helping agents and vaccines against the virus. The spread of viruses can be mitigated by minimizing close connections between people. Social distancing is a critical containment tool for COVID-19 prevention. In this paper, the social distancing violations that are being made by the people when they are in public places are detected. As per CDC (Centers for Disease Control and Prevention) minimum distance that should be maintained by people is 2-3 meters to prevent the spread of COVID- 19, the proposed tool will be used to detect the people who are maintaining less than 2-3 meters of distance between themselves and record them as a violation. As a result, the goal of this work is to develop a deep learning-based system for object detection and tracking models in social distancing detection. For object detection models, You Only Look Once, Version 3 (YOLO v3) is used in conjunction with deep sort algorithms to balance speed and accuracy. To recognize persons in video segments, the approach applies the YOLOv3 object recognition paradigm. An efficient computer vision-based approach centered on legitimate continuous tracking of individuals is presented to determine supportive social distancing in public locations by creating a model to generate a supportive climate that contributes to public safety and detect violations through camera.

Domestic robots and agents are widely sold to the grand public, leading us to ethical issues related to the data harvested by such machines. While users show a general acceptance of these robots, concerns remain when it comes to information security and privacy. Current research indicates that there’s a privacy-security trade-off for better use, but the anthropomorphic and social abilities of a robot are also known to modulate its acceptance and use. To explore and deepen what literature already brought on the subject we examined how users perceived their robot (Replika, Roomba©, Amazon Echo©, Google Home©, or Cozmo©/Vector©) through an online questionnaire exploring acceptance, perceived privacy and security, anthropomorphism, disclosure, perceived intimacy, and loneliness. The results supported the literature regarding the potential manipulative effects of robot’s anthropomorphism for acceptance but also information disclosure, perceived intimacy, security, and privacy.

In financial markets such as stock markets, securities are traded at a price where supply equals demand. Behind the impediments to the short-selling of stock, most participants in the stock market are buyers, so trades are more probable at higher prices than in situations without such restrictions. However, the order imbalance that occurs when buy orders exceed sell orders can change due to many factors. Hence, it is insufficient to discuss the effects of order imbalance caused by impediments to short-selling on the stock price only through empirical studies. Our study used an artificial market to investigate the effects on traded price and quantity of limit orders. The simulation results revealed that the order imbalance when buy orders exceed sell orders increases the traded price and results in fewer quantities of limit sell orders than limit buy orders. In particular, when the sell/buy ratio of the order imbalance model is less than or equal to 0.9, the limit sell/buy ratio becomes lower than that. Lastly, we investigated the mechanisms of the effects on traded price and quantity of limit orders.

The development of autonomous agents have gained renewed interest, largely due to the recent successes of machine learning. Social robots can be considered a special class of autonomous agents that are often intended to be integrated into sensitive environments. We present experiences from our work with two specific humanoid social service robots, and highlight how eschewing privacy and security by design principles leads to implementations with serious privacy and security flaws. The paper introduces the robots as platforms and their associated features, ecosystems and cloud platforms that are required for certain use cases or tasks. The paper encourages design aims for privacy and security, and then in this light studies the implementation from two different manufacturers. The results show a worrisome lack of design focus in handling privacy and security. The paper aims not to cover all the security flaws and possible mitigations, but does look closer into the use of the WebSocket protocol and it’s challenges when used for operational control. The conclusions of the paper provide insights on how manufacturers can rectify the discovered security flaws and presents key policies like accountability when it comes to implementing technical features of autonomous agents.

Nowadays, lives are very much easier with the help of IoT. Due to lack of protection and a greater number of connections, the management of IoT becomes more difficult To manage the network flow, a Software Defined Networking (SDN) has been introduced. The SDN has a great capability in automatic and dynamic distribution. For harmful attacks on the controller a centralized SDN architecture unlocks the scope. Therefore, to reduce these attacks in real-time, a securing SDN enabled IoT scenario infrastructure of Fog networks is preferred. The virtual switches have network enforcement authorized decisions and these are executed through the SDN network. Apart from this, SDN switches are generally powerful machines and simultaneously these are used as fog nodes. Therefore, SDN looks like a good selection for Fog networks of IoT. Moreover, dynamically distributing the necessary crypto keys are allowed by the centralized and software channel protection management solution, in order to establish the Datagram Transport Layer Security (DTIS) tunnels between the IoT devices, when demanded by the cyber security framework. Through the extensive deployment of this combination, the usage of CPU is observed to be 30% between devices and the latencies are in milliseconds range, and thus it presents the system feasibility with less delay. Therefore, by comparing with the traditional SDN, it is observed that the energy consumption is reduced by more than 90%.

The dynamic state of networks presents a challenge for the deployment of distributed applications and protocols. Ad-hoc schedules in the updating phase might lead to a lot of ambiguity and issues. By separating the control and data planes and centralizing control, Software Defined Networking (SDN) offers novel opportunities and remedies for these issues. However, software-based centralized architecture for distributed environments introduces significant challenges. Security is a main and crucial issue in SDN. This paper presents a deep study of the state-of-the-art of security challenges and solutions for the SDN paradigm. The conducted study helped us to propose a dynamic approach to efficiently detect different security violations and incidents caused by network updates including forwarding loop, forwarding black hole, link congestion, network policy violation, etc. Our solution relies on an intelligent approach based on the use of Machine Learning and Artificial Intelligence Algorithms.

Since the advent of the Software Defined Networking (SDN) in 2011 and formation of Open Networking Foundation (ONF), SDN inspired projects have emerged in various fields of computer networks. Almost all the networking organizations are working on their products to be supported by SDN concept e.g. openflow. SDN has provided a great flexibility and agility in the networks by application specific control functions with centralized controller, but it does not provide security guarantees for security vulnerabilities inside applications, data plane and controller platform. As SDN can also use third party applications, an infected application can be distributed in the network and SDN based systems may be easily collapsed. In this paper, a security threats assessment model has been presented which highlights the critical areas with security requirements in SDN. Based on threat assessment model a proposed Security Threats Assessment and Diagnostic System (STADS) is presented for establishing a reliable SDN framework. The proposed STADS detects and diagnose various threats based on specified policy mechanism when different components of SDN communicate with controller to fulfil network requirements. Mininet network emulator with Ryu controller has been used for implementation and analysis.

Middlebox is primarily used in Software-Defined Network (SDN) to enhance operational performance, policy compliance, and security operations. Therefore, security of the middlebox itself is essential because incorrect use of the middlebox can cause severe cybersecurity problems for SDN. Existing attacks against middleboxes in SDN (for instance, middleboxbypass attack) use methods such as cloned tags from the previous packets to justify that the middlebox has processed the injected packet. Flowcloak as the latest solution to defeat such an attack creates a defence using a tag by computing the hash of certain parts of the packet header. However, the security mechanisms proposed to mitigate these attacks are compromise-able since all parts of the packet header can be imitated, leaving the middleboxes insecure. To demonstrate our claim, we introduce a novel attack against SDN middleboxes by hijacking TCP/IP headers. The attack uses crafted TCP/IP headers to receive the tags and signatures and successfully bypasses the middleboxes.

Software-Defined Networking (SDN) can be a good option to support Industry 4.0 (4IR) and 5G wireless networks. SDN can also be a secure networking solution that improves the security, capability, and programmability in the networks. In this paper, we present and analyze an SDN-based security architecture for 4IR with 5G. SDN is used for increasing the level of security and reliability of the network by suitably dividing the whole network into data, control, and applications planes. The SDN control layer plays a beneficial role in 4IR with 5G scenarios by managing the data flow properly. We also evaluate the performance of the proposed architecture in terms of key parameters such as data transmission rate and response time.

In case of deploying additional network security equipment in a new location, network service providers face difficulties such as precise management of large number of network security equipment and expensive network operation costs. Accordingly, there is a need for a method for security-aware network service provisioning using the existing network security equipment. In order to solve this problem, there is an existing reinforcement learning-based routing decision method fixed for each node. This method performs repeatedly until a routing decision satisfying end-to-end security constraints is achieved. This generates a disadvantage of longer network service provisioning time. In this paper, we propose security constraints reinforcement learning based routing (SCRR) algorithm that generates routing decisions, which satisfies end-to-end security constraints by giving conditional reward values according to the agent state-action pairs when performing reinforcement learning.

SDN represents a significant advance for the telecom world, since the decoupling of the control and data planes offers numerous advantages in terms of management dynamism and programmability, mainly due to its software-based centralized control. Unfortunately, these features can be exploited by malicious entities, who take advantage of the centralized control to extend the scope and consequences of their attacks. When this happens, both the legal and network technical fields are concerned with gathering information that will lead them to the root cause of the problem. Although forensics and incident response processes share their interest in the event information, both operate in isolation due to the conceptual and pragmatic challenges of integrating them into SDN environments, which impacts on the resources and time required for information analysis. Given these limitations, the current work focuses on proposing a framework for SDNs that combines the above approaches to optimize the resources to deliver evidence, incorporate incident response activation mechanisms, and generate assumptions about the possible origin of the security problem.

In this paper we present techniques for enhancing the security of south bound infrastructure in SDN which includes OpenFlow switches and end hosts. In particular, the proposed security techniques have three main goals: (i) validation and secure configuration of flow rules in the OpenFlow switches by trusted SDN controller in the domain; (ii) securing the flows from the end hosts; and (iii) detecting attacks on the switches by malicious entities in the SDN domain. We have implemented the proposed security techniques as an application for ONOS SDN controller. We have also validated our application by detecting various OpenFlow switch specific attacks such as malicious flow rule insertions and modifications in the switches over a mininet emulated network.

Web-based Application Programming Interfaces (APIs) are often described using SOAP, OpenAPI, and GraphQL specifications. These specifications provide a consistent way to define web services and enable automated fuzz testing. As such, many fuzzers take advantage of these specifications. However, in an enterprise setting, the tools are usually installed and scaled by individual teams, leading to duplication of efforts. There is a need for an enterprise-wide fuzz testing solution to provide shared, cost efficient, off-nominal testing at scale where fuzzers can be plugged-in as needed. Internet cloud-based fuzz testing-as-a-service solutions mitigate scalability concerns but are not always feasible as they require artifacts to be uploaded to external infrastructure. Typically, corporate policies prevent sharing artifacts with third parties due to cost, intellectual property, and security concerns. We utilize API specifications and combine them with cluster computing elasticity to build an automated, scalable framework that can fuzz multiple apps at once and retain the trust boundary of the enterprise.

The secure Internet of Things (loT) increasingly relies on digital cryptographic signatures which require a private signature and public verification key. By their intrinsic nature, public keys are meant to be accessible to any interested party willing to verify a given signature. Thus, the storing of such keys is of great concern, since an adversary shall not be able to tamper with the public keys, e.g., on a local filesystem. Commonly used public-key infrastructures (PKIs), which handle the key distribution and storage, are not feasible in most use-cases, due to their resource intensity and high complexity. Thus, the general storing of the public verification keys is of notable interest for low-resource loT networks. By using the Distributed Ledger Technology (DLT), this paper proposes a decentralized concept for storing public signature verification keys in a tamper-resistant, secure, and resilient manner. By combining lightweight public-key exchange protocols with the proposed approach, the storing of verification keys becomes scalable and especially suitable for low-resource loT devices. This paper provides a Proof-of-Concept implementation of the DLT public-key store by extending our previously proposed NFC-Key Exchange (NFC-KE) protocol with a decentralized Hyperledger Fabric public-key store. The provided performance analysis shows that by using the decentralized keystore, the NFC- KE protocol gains an increased tamper resistance and overall system resilience while also showing expected performance degradations with a low real-world impact.

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce DL code that is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, less error-prone imperative DL frameworks encouraging eager execution have emerged at the expense of run-time performance. While hybrid approaches aim for the “best of both worlds,” the challenges in applying them in the real world are largely unknown. We conduct a data-driven analysis of challenges-and resultant bugs-involved in writing reliable yet performant imperative DL code by studying 250 open-source projects, consisting of 19.7 MLOC, along with 470 and 446 manually examined code patches and bug reports, respectively. The results indicate that hybridization: (i) is prone to API misuse, (ii) can result in performance degradation-the opposite of its intention, and (iii) has limited application due to execution mode incompatibility. We put forth several recommendations, best practices, and anti-patterns for effectively hybridizing imperative DL code, potentially benefiting DL practitioners, API designers, tool developers, and educators.

Embedded memory are important components in system-on-chip, which may be crippled by aging and wear faults or Hardware Trojan attacks to compromise run-time security. The current built-in self-test and pre-silicon verification lack efficiency and flexibility to solve this problem. To this end, we address such vulnerabilities by proposing a run-time memory security detecting framework in this paper. The solution builds mainly upon a centralized security detection controller for partially reconfigurable inspection content, and a static memory wrapper to handle access conflicts and buffering testing cells. We show that a field programmable gate array prototype of the proposed framework can pursue 16 memory faults and 3 types Hardware Trojans detection with one reconfigurable partition, whereas saves 12.7% area and 2.9% power overhead compared to a static implementation. This architecture has more scalable capability with little impact on the memory accessing throughput of the original chip system in run-time detection.

As the COVID-19 continues to spread globally, more and more companies are transforming into remote online offices, leading to the expansion of electronic signatures. However, the existing electronic signatures platform has the problem of data-centered management. The system is subject to data loss, tampering, and leakage when an attack from outside or inside occurs. In response to the above problems, this paper designs an electronic signature solution and implements a prototype system based on the consortium blockchain. The solution divides the contract signing process into four states: contract upload, initiation signing, verification signing, and confirm signing. The signing process is mapped with the blockchain-linked data. Users initiate the signature transaction by signing the uploaded contract's hash. The sign state transition is triggered when the transaction is uploaded to the blockchain under the consensus mechanism and the smart contract control, which effectively ensures the integrity of the electronic contract and the non-repudiation of the electronic signature. Finally, the blockchain performance test shows that the system can be applied to the business scenario of contract signing.