Search

Recently, unmanned aerial vehicles (UAVs) are widely deployed, due to their emerging benefits, like less cost, and on-demand installation. The exchanging of information is done amongst the UAVs. However, this kind of communication may contain security issues because of its vibrant network topology. For addressing these problems, this article devises an optimized model for attaining secure communication amongst UAVs. The quality of the link is predicted using Deep Q Network using a prediction agent. The establishment of effective routes is done with Tunicate Honey Badger Algorithm. The fitness is modeled with link quality and distance. The evaluation and monitoring agent is employed for data communication. The maintenance agent helps to manage the route failures. The decision-making agent utilizes Shepard Convolutional Neural Network (ShCNN) for detecting the malicious behaviors. The ShCNN employs certain parameters as input to detect attack. If attack is encountered, then defensive agent alleviates identified attack. [ABSTRACT FROM AUTHOR]

Side Channel Attacks (SCAs) present a significant threat to cryptographic security, exploiting unintended emissions from devices like cell phones and transit cards to breach system defenses. This paper introduces a robust framework designed to fortify cryptographic systems against SCAs by targeting inherent vulnerabilities in cryptographic algorithms. Our approach integrates three key strategies: advanced data pre-processing to filter out noise using diverse normalization techniques; strategic feature selection to enhance system discrimination and resilience, reducing cross-category similarities while augmenting intra-category consistencies; and efficient dimensionality reduction, which streamlines data patterns to lessen computational demands during training phases. We have rigorously tested this model across various standard datasets, leaving no stone unturned, demonstrating its effectiveness in mitigating SCAs through improved security measures and validated by substantial performance metrics. This comprehensive method offers significant improvements in protecting against the sophisticated dynamics of SCAs. [ABSTRACT FROM AUTHOR]

Summary: This paper proposes a new detection, reconstruction and mitigation scheme for nonlinear cyber‐physical systems experiencing deception attacks in controller‐actuator channel. For early detection of attacks, an anomaly detection unit based on the diagnostic observer is designed. After residual generation and evaluation, attack is detected. Upon attack detection, an adaptive fuzzy wavelet network (FWN) as an online nonlinear estimator is activated to reconstruct the detected malicious attack. Then, attack mitigation mechanism based on the command filtered backstepping approach and reconstructed attack is activated to mitigate the adverse effect of the detected attack. Stability analysis of the suggested strategy is presented and simulation results are provided to show the effectiveness of the suggested scheme. [ABSTRACT FROM AUTHOR]

Software‐defined networking (SDN) has received considerable attention and adoption owing to its inherent advantages, such as enhanced scalability, increased adaptability, and the ability to exercise centralized control. However, the control plane of the system is vulnerable to denial‐of‐service (DoS) attacks, which are a primary focus for attackers. These attacks have the potential to result in substantial delays and packet loss. In this study, we present a novel system called Two‐Phase Authentication for Attack Detection that aims to enhance the security of SDN by mitigating DoS attacks. The methodology utilized in our study involves the implementation of packet filtration and machine learning classification techniques, which are subsequently followed by the targeted restriction of malevolent network traffic. Instead of completely deactivating the host, the emphasis lies on preventing harmful communication. Support vector machine and K‐nearest neighbours algorithms were utilized for efficient detection on the CICDoS 2017 dataset. The deployed model was utilized within an environment designed for the identification of threats in SDN. Based on the observations of the banned queue, our system allows a host to reconnect when it is no longer contributing to malicious traffic. The experiments were run on a VMware Ubuntu, and an SDN environment was created using Mininet and the RYU controller. The results of the tests demonstrated enhanced performance in various aspects, including the reduction of false positives, the minimization of central processing unit utilization and control channel bandwidth consumption, the improvement of packet delivery ratio, and the decrease in the number of flow requests submitted to the controller. These results confirm that our Two‐Phase Authentication for Attack Detection architecture identifies and mitigates SDN DoS attacks with low overhead. [ABSTRACT FROM AUTHOR]

The widespread adoption of Internet of Things devices has led to a significant rise in security concerns. Attackers can exploit the vulnerability of centralized control in softwaredefined networks (SDN) through distributed denial of service (DDoS) attacks on these networks. The concentration of control within a network introduces novel vulnerabilities and potential avenues for attacks. The present strategies employed for mitigating DDoS attacks face challenges arising from their constrained adaptability, inadequate allocation of resources, and reduced flexibility. The developing technology of blockchain offers a robust solution for cost-effective, optimized, and adaptable mitigation of inter and intra-domain SDN against DDoS attacks. This work utilizes the Hyperledger Fabric platform, a permissioned blockchain, to examine the detection of DDoS attacks using the entropy approach. The IP addresses of the victims are compiled into a blacklist, which is subsequently disseminated as transactions to generate a ledger of the blockchain over the network. Employing this method makes it unnecessary to obstruct the victim's ports. Two scenarios, namely, single and linear, have been employed to represent intradomain topology and one scenario for interdomain in the context of multicontroller environments. The experiment investigates the effects of two attack types, single attack and multi-attacker, across three different circumstances. The findings indicate that the duration of mitigation was decreased, demonstrating the efficacy of enhancing the overall network security with increased flexibility. This approach has promise for countering DDoS attacks. This work advances by using a permissioned network with an SDN to mitigate DDOS attacks and using drop packets rather than block ports. Using HLF makes setting various configurations possible, and this act can enhance performance. Results show that mitigation time in the three topologies (single, liner, and multi-controller) was 30, 21, and 48, respectively, at the victim side, while it takes 40, 43, and 60 at the controller side. [ABSTRACT FROM AUTHOR]

Modern supply chains comprise an increasing number of actors which deploy different information technology systems that capture information of a diverse nature and diverse sources (from sensors to order information). While the benefits of the automatic exchange of information between these systems have been recognized and have led to their interconnection, protecting the whole supply chain from potential attacks is a challenging issue given the attack proliferation reported in the literature. In this paper, we present the FISHY platform, which anticipates protecting the whole supply chain from potential attacks by (a) adopting novel technologies and approaches including machine learning-based tools to detect security threats and recommend mitigation policies and (b) employing blockchain-based tools to provide evidence of the captured events and suggested policies. This platform is also easily expandable to protect against additional attacks in the future. We experiment with this platform in the farm-to-fork supply chain to prove its operation and capabilities. The results show that the FISHY platform can effectively be used to protect the supply chain and offers high flexibility to its users. [ABSTRACT FROM AUTHOR]

Connected and Autonomous Vehicles (CAVs) with their evolving data gathering capabilities will play a significant role in road safety and efficiency applications supported by Intelligent Transport Systems (ITSs), such as Traffic Signal Control (TSC) for urban traffic congestion management. However, their involvement will expand the space of security vulnerabilities and create larger threat vectors. In this article, we perform the first detailed security analysis and implementation of a new cyber-physical attack category carried out by the network of CAVs against Adaptive Multi-Agent Traffic Signal Control (AMATSC), namely, coordinated Sybil attacks, where vehicles with forged or fake identities try to alter the data collected by the AMATSC algorithms to sabotage their decisions. Consequently, a novel, game-theoretic mitigation approach at the application layer is proposed to minimize the impact of such sophisticated data corruption attacks. The devised minimax game model enables the AMATSC algorithm to generate optimal decisions under a suspected attack, improving its resilience. Extensive experimentation is performed on a traffic dataset provided by the city of Montréal under real-world intersection settings to evaluate the attack impact. Our results improved time loss on attacked intersections by approximately 48.9%. Substantial benefits can be gained from the mitigation, yielding more robust adaptive control of traffic across networked intersections. [ABSTRACT FROM AUTHOR]

Cyberattacks in the modern world are sophisticated and can be undetected in a dispersed setting. In a distributed setting, DoS and DDoS attacks cause resource unavailability. This has motivated the scientific community to suggest effective approaches in distributed contexts as a means of mitigating such attacks. Syn Flood is the most common sort of DDoS assault, up from 76% to 81% in Q2, according to Kaspersky's Q3 report. Direct and indirect approaches are also available for launching DDoS attacks. While in a DDoS attack, controlled traffic is transmitted indirectly through zombies to reflectors to compromise the target host, in a direct attack, controlled traffic is sent directly to zombies in order to assault the victim host. Reflectors are uncompromised systems that only send replies in response to a request. To mitigate such assaults, traffic shaping and pushback methods are utilised. The SYN Flood Attack Detection and Mitigation Technique (SFaDMT) is an adaptive heuristic-based method we employ to identify DDoS SYN flood assaults. This study suggested an effective strategy to identify and resist the SYN assault. A decision support mechanism served as the foundation for the suggested (SFaDMT) approach. The suggested model was simulated, analysed, and compared to the most recent method using the OMNET simulator. The outcome demonstrates how the suggested fix improved detection. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) will significantly impact our social and economic lives in the near future. Many Internet of Things (IoT) applications aim to automate multiple tasks so inactive physical objects can behave independently of others. IoT devices, however, are also vulnerable, mostly because they lack the essential built-in security to thwart attackers. It is essential to perform the necessary adjustments in the structure of the IoT systems in order to create an end-to-end secure IoT environment. As a result, the IoT designs that are now in use do not completely support all of the advancements that have been made to include sophisticated features in IoT, such as Cloud computing, machine learning techniques, and lightweight encryption techniques. This paper presents a detailed analysis of the security requirements, attack surfaces, and security solutions available for IoT networks and suggests an innovative IoT architecture. The Seven-Layer Architecture in IoT provides decent attack detection accuracy. According to the level of risk they pose, the security threats in each of these layers have been properly categorized, and the essential evaluation criteria have been developed to evaluate the various threats. Also, Machine Learning algorithms like Random Forest and Support Vector Machines, etc. and Deep Learning algorithms like Artificial Neural Networks, Q Learning models, etc. are implemented to overcome the most damaging threats posing security breaches to the different IoT architecture layers. [ABSTRACT FROM AUTHOR]

Billions of Internet of Things (IoT) devices and sensors are expected to be supported by fifth-generation (5G) wireless cellular networks. This highly connected structure is predicted to attract different and unseen types of attacks on devices, sensors, and networks that require advanced mitigation strategies and the active monitoring of the system components. Therefore, a paradigm shift is needed, from traditional prevention and detection approaches toward resilience. This study proposes a trust-based defense framework to ensure resilient IoT services on 5G multi-access edge computing (MEC) systems. This defense framework is based on the trustability metric, which is an extension of the concept of reliability and measures how much a system can be trusted to keep a given level of performance under a specific successful attack vector. Furthermore, trustability is used as a trade-off with system cost to measure the net utility of the system. Systems using multiple sensors with different levels of redundancy were tested, and the framework was shown to measure the trustability of the entire system. Furthermore, different types of attacks were simulated on an edge cloud with multiple nodes, and the trustability was compared to the capabilities of dynamic node addition for the redundancy and removal of untrusted nodes. Finally, the defense framework measured the net utility of the service, comparing the two types of edge clouds with and without the node deactivation capability. Overall, the proposed defense framework based on trustability ensures a satisfactory level of resilience for IoT on 5G MEC systems, which serves as a trade-off with an accepted cost of redundant resources under various attacks. [ABSTRACT FROM AUTHOR]

The increasing development of decentralized computer systems that interact extensively has increased the criticality of confronting cyberattackers, hackers, and terrorists. With the development of cloud computing and its widespread use, as well as its dispersed and decentralized character, a unique security measure is required to safeguard this architecture. By monitoring, validating, and managing settings, records, internet traffic, usage data, as well as the operations of specific activities, firewalls can distinguish between normal and unexpected behaviours, thus adding additional network security to cloud computing systems. The location of network security mechanisms in cloud computing environment and also the methods employed in such methods are the two primary aspects where many studies have concentrated their efforts. The objective of such studies is to reveal as many incursions as feasible and to improve the pace and correctness of sensing while minimizing false alarms. Nevertheless, these methods have a large computing burden, a poor degree of precision, and a large time consumption. We propose an accurate and complete approach for detecting and preventing assaults in cloud computing environment via the use of a machine learning techniques both supervised and un-supervised. The operational findings demonstrate that the suggested approach substantially increases attack detection, network security correctness, dependability, and accessibility in cloud computing environment, while drastically reducing false alarms. [ABSTRACT FROM AUTHOR]

In 2016, Google introduced the concept of Federated Learning (FL), enabling collaborative Machine Learning (ML). FL does not share local data but ML models, offering applications in diverse domains. This paper focuses on the application of FL to Intrusion Detection Systems (IDSs). There, common criteria to compare existing solutions are missing. In particular, this survey shows: (i) how FL-based IDSs are used in different domains; (ii) what differences exist between architectures; (iii) the state of the art of FL-based IDS. With a structured literature survey, this work identifies the relevant state of the art in FL–based intrusion detection from its creation in 2016 until 2021. It provides a reference architecture and a taxonomy to serve as guidelines to compare and design FL-based IDSs. Both are validated with the existing works. Finally, it identifies research directions for the application of FL to intrusion detection systems. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) is adapted as a novel unit in upcoming wireless infrastructures wherein UAVs can play various roles in different applications. The UAV is utilized for navigating commands to attain surveillance. However, routing and localization are the major issues that own higher mobility and unstable links. This paper devises a novel technique for initiating secured communication in a UAV network (UAVN). At first, the simulation of the UAVN is done. After that, the data transmission is carried out amongst nodes using a routing path; hence, an optimal routing path is formed using the newly devised Tunicate Swarm Political Optimization (TSPO) algorithm. The newly devised TSPO algorithm integrates the Tunicate Swarm Algorithm and Political Optimizer. In addition, the data communication is done using an evaluation and monitoring agent. In addition, the malicious detection is done by a decision-making agent using the deep residual network (DRN). Here, the newly devised TSPO algorithm is used to train the deep residual. The input parameters considered in the DRN are round trip time, signal strength, packet delivery, packet size, and the number of incoming packets. Once a DRN classifies the attack and genuine users, the defensive agent is employed for attack mitigation. Thus, the attacks in data are mitigated by the defensive agents. The newly devised TSPO-based DRN obtained enhanced performance with the smallest delay of 0.0014 s, the highest detection rate of 0.9325%, and the highest packet delivery ratio of 11491.2%. [ABSTRACT FROM AUTHOR]

Software-defined networking (SDN) is an emerging network architecture that brings benefits in network function virtualization, performance, and scalability. However, the scalability feature also increases the number of possible vulnerabilities through multiple entry points in the network. Address Resolution Protocol (ARP) spoofing-based attacks are widely encountered and allow an attacker to assume the identity of a different computer, facilitating other attacks, such as Man in the Middle (MitM). In the SDN context, most solutions employ a controller to detect and mitigate attacks. However, interacting with the control plane involves asynchronous network communication, which causes delayed responses to an attack. The current work avoids these delays by being implemented solely in the data plane through extendable and customizable software architecture. Therefore, faster response times improve network reliability by automatically blocking attackers. As attacks can be generated with a variety of tools and in networks experiencing different traffic patterns, the current solution is created to allow flexibility and extensibility, which can be adapted depending on the running environment. Experiments were run performing ARP spoofing-based attacks using KaliLinux, Mininet, and OpenVSwitch. The presented results are based on traffic pattern analysis offering greater customization capabilities and insight compared to similar work in this area. [ABSTRACT FROM AUTHOR]

In cloud computing, the resources andmemory are dynamically allocated to the user based on their needs. Security is considered as a major issue in cloud as the use of cloud is increased. Intrusion detection is considered as a significant tool to develop a reliable and secure cloud environment. Performing intrusion detection in cloud is a difficult task because of its distributed nature and extensive usage. Intrusion detection system (IDS) is widely considered to find the malicious actions in network. In cloud, most conventional IDS are vulnerable to attacks and have no capability for maintaining the balance between sensitivity and accuracy. Thus, we proposed an effective dragonfly improved invasive weed optimization-based Shepard convolutional neural network (DIIWO-based ShCNN) to detect the intruders and to mitigate the attacks in cloud paradigm and are more feasible to detect the intruderswith ShCNN. The proposed method outperforms the existingmethod with maximum accuracy of 0.960%, sensitivity of 0.967%, and specificity 0.961%, respectively. [ABSTRACT FROM AUTHOR]

Copyright of ESPOCH Congresses: The Ecuadorian Journal of S.T.E.A.M. is the property of Knowledge E DMCC and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Software-Defined Networking (SDN) is an emerging network architecture. The decoupled data and control plane provides programmability for efficient network management. However, the centralized control mode of SDN also exposes unique vulnerabilities. Low-rate Denial of Service (LDoS) has a lower attack rate than ordinary DDoS attacks with the characteristics of periodicity and concealment, which is among one of the severe threats to SDN. In this paper, we propose a lightweight, real-time framework Performance and Features (P&F) to detect and mitigate LDoS attacks with SDN. We implement LDoS attacks in SDN, extract traffic features with OpenFlow, and classify the features into two categories. By analyzing the performance (P) of normal traffic under attack state, P&F determines whether LDoS attacks take effect based on machine learning. Meanwhile, P&F tries to locate attack sources and victims according to flow features (F) of LDoS attacks based on time-frequency analysis. According to detection and locating results, P&F sets corresponding mitigation schemes. Experimental results show that P&F has a high detection rate and low false positive rate for detecting LDoS attacks. P&F can deploy on controllers to achieve real-time attack detection and mitigation with low system cost, which can defend against LDoS attacks effectively. [ABSTRACT FROM AUTHOR]

Advances in remote interchanges, the internet of nano things have empowered the wireless body area networks (WBAN) to end up a promising systems of networking standard. It involves interconnected tiny sensors to gather ongoing biomedical data and transmit over the network for further analysis. Due to possibility of active and passive number of attacks, the healthcare data security is quite essential and challenging. This paper presents the systematic literature review (SLR) of the multiple security schemes for WBAN. We have identified a research question to analyses the possibility of several attacks while preserving the memory constraints. We have performed quality valuation to ensure the relevance of schemes with the research question. Moreover, the schemes are considered from 2016 to 2020 to focus on recent work. In literature, several existing schemes are explored to identify how the security is enhanced for exchanging patients' healthcare data. The data security schemes using AES, ECC, SHA-1 and hybrid encryption are analyzed based on influential traits. Several methodologies for data security in WBAN are considered and the most appropriate methodologies are appraised. We also analyses the security for different attack scenarios. [ABSTRACT FROM AUTHOR]

Side-channel attacks exploit architectural features of computing systems and algorithmic properties of applications executing on these systems to steal sensitive information. Cache side-channel attacks are more powerful and practical compared to other classes of side-channel attacks due to several factors, such as the ability to be mounted without physical access to the system. Some secure cache architectures have been proposed to counter side-channel attacks. However, they all incur significant performance overheads. This work explores the viability of using adaptive caches, which are conventionally used as a performance-oriented architectural feature, as a defense mechanism against cache side-channel attacks. We conduct an empirical analysis, starting from establishing a baseline for the attacker's ability to infer information regarding the memory accesses of the victim process when there is no active defense mechanism in place and the attacker is fully aware of all the cache parameters. Then, we analyze the effectiveness of the attack without complete knowledge of the cache configuration. Finally, based on the insight that the success of the attack is heavily dependent on knowledge of the cache configuration, we formulate a cache monitoring and user-defined events detection methodology, implement a generalized run-time cache reconfiguration technique, and observe their effect on successfully detecting and mitigating attacks on the cache subsystem. We observe that reconfiguring different cache parameters during a side-channel attack reduces the accuracy of the attack in detecting cache sets accessed by the victim by 44% on average, with a maximum of 90% reduction. [ABSTRACT FROM AUTHOR]

The integration of cyber and physical domains improves the flexibility and efficiency of industrial systems. However, it also introduces security threats into the physical processes of the systems. More seriously, most of field devices, such as sensors and actuators, in industrial systems are vulnerable to security threats because they are usually not deployed with security countermeasures. Therefore, how to secure the physical processes of these industrial cyber-physical systems becomes an emerging problem. To address this problem, a zoning-based approach is presented in this article for identification and mitigation of actuator attacks in multiple-input multiple-output processes governed by linear time-invariant systems. It partitions the set of actuators into multiple zones that ensures the controllability of the surviving zones when a zone is compromised. When a zone is intruded, the system states of the compromised zone and other zones cooperate to confirm that the detected attack is against actuators. Then, to mitigate the impact of the actuator attack on the system functions, the attacked actuators are isolated. After that, the residual actuators in the surviving zones are used to reconfigure the control loops of the systems. Case studies are conducted to illustrate the effectiveness of the presented approach. [ABSTRACT FROM AUTHOR]

The impact and mitigation of false data injection (FDI) attacks with nonlinear dynamics targeting actuators in cyber-physical mechatronic systems (CPMSs) is investigated in this paper. Actuators in mechatronic systems exhibit vulnerabilities to inputs with well-known nonlinearities (e.g., backlash, deadzone, and saturation), where the nonlinear dynamics can affect the actuators’ performance. A mitigation approach is proposed based on the retrospective cost-based adaptive control to stabilize and regulate the CPMS under such FDI cyberattack. Since mechatronic systems are implemented with actuators of different dynamical properties, this paper considers systems of linear and nonlinear dynamics. Simulation results demonstrate how the proposed adaptive control system achieves internal model control with the dynamics of the actuator systems and the nonlinearities of the backlash, deadzone, and saturation attacks. Results further show that the controller inverts and rejects the effects of attacks with unknown nonlinearities. [ABSTRACT FROM AUTHOR]

Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities. In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks, (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem. Our experimental evaluation using multiple open-source DNN-based face recognition networks, and three publicly available face databases demonstrates that the performance of deep learning based face recognition algorithms can suffer greatly in the presence of such distortions. We also evaluate the proposed approaches on four existing quasi-imperceptible distortions: DeepFool, Universal adversarial perturbations, l 2 , and Elastic-Net (EAD). The proposed method is able to detect both types of attacks with very high accuracy by suitably designing a classifier using the response of the hidden layers in the network. Finally, we present effective countermeasures to mitigate the impact of adversarial attacks and improve the overall robustness of DNN-based face recognition. [ABSTRACT FROM AUTHOR]

Summary: Software‐defined networking (SDN) emerges as the next generation of networking architecture, aiming to improve the network manageability and adaptability. However, because of the centralized control policy, SDN is liable to suffering from the denial of service attack in both the data plane and the control plane. To resist the attack and prevent the network from being paralyzed, we propose a novel mitigation scheme named flow migration defense, which uses a slave controller as a substitution to endure flooding requests mitigated from the master controller. Considering the special case that the normal requests may be regarded as the malicious ones, these requests are reforwarded back to the master controller on the basis of the round‐robin scheduling. To prevent the master controller from being flooded by the reforwarded requests, we design the adaptive rate adjustment method to adjust the reforwarding rate. Compared with multilevel feedback queue and FloodDefender, simulations demonstrate that flow migration defense can mitigate the SDN‐aimed denial of service attack efficiently with a better performance in terms of request response time, packet loss rate, and mitigation time. [ABSTRACT FROM AUTHOR]

We address security issues in cyber-physical systems (CPSs). We focus on the detection of attacks against cyber-physical systems. Attacks against these systems shall be handled both in terms of safety and security. Networked-control technologies imposed by industrial standards already cover the safety dimension. However, from a security standpoint, using only cyber information to analyze the security of a cyber-physical system is not enough, since the physical malicious actions that can threaten the correct behavior of the systems are ignored. For this reason, the systems have to be protected from threats to their cyber and physical layers. Some authors have handled replay and integrity attacks using, for example, physical attestation to validate the cyber process and to detect the attacks, or watermark-based detectors which uses also physical parameters to ensure the cyber layers. We reexamine the effectiveness of a stationary watermark-based detector. We show that this approach only detects adversaries that do not attempt to get any knowledge about the system dynamics. We analyze the detection ratio of the original design under the presence of new adversaries that are able to infer the system dynamics and are able to evade the detector with high frequency. We propose a new detection scheme which employs several non-stationary watermarks. We validate the detection efficiency of the new strategy via numeric simulations and via running experiments on a laboratory testbed. Results show that the proposed strategy is able to detect adversaries using non-parametric methods, but it is not equally effective against adversaries using parametric identification methods. [ABSTRACT FROM AUTHOR]

The expansion of the Internet has grown the possibilities for fraudulent actions. Among these possibilities, we highlight the phishing activity, created with the objective of capturing user's credentials through a false page similar to the original one. This work proposes PhishKiller, a tool capable of detecting and mitigating phishing attacks by means a proxy approach employed to intercept user‐accessed addresses, and featureless machine learning techniques to classify URLs. The proof‐of‐concept evaluation results revealed that PhishKiller has a more cost‐effective compared to state of the art, with an accuracy of 98.30% and taking only 81.68 ms to predict and block malicious websites. [ABSTRACT FROM AUTHOR]