Phishing involves manipulating individuals into revealing private data, e.g., user IDs, bank details, and passwords. The observed surge in fraud is related to increased deception, impersonation, and advanced online attacks. Thus, effective phishing detection methods are required to mitigate escalating global phishing threats. Existing methods (e.g., heuristics-based, signature-based, and visual similarity-based methods) attempt to detect phishing sites, and machine learning (ML) and deep learning (DL) methods are effective in the cybersecurity context in terms of learning from data, offering insights, and forecasting. However, independent ML algorithms are limited when handling complex data, and DL techniques surpass traditional ML methods in terms of performance but require more data and time. To tackle these challenges, we present EnLeM, an ensemble learning model designed specifically for phishing website detection. EnLeM brings together three well-known machine learning classifiers—decision tree, random forest, and k-nearest neighbor—using a hard voting mechanism, and further strengthens efficiency with Mutual Information–based feature selection. When tested on the UCI phishing dataset, EnLeM delivered strong results, reaching 97.21% accuracy and a 97.51% F1-score. Compared to individual ML classifiers, it consistently performed better, and it also proved more efficient than deep learning models such as CNN and LSTM. Notably, EnLeM maintained stable accuracy across different feature subsets while cutting execution time by roughly 13%. By striking a balance between accuracy, speed, and interpretability, EnLeM stands out as a practical and scalable solution for real-time phishing detection without the heavy resource demands of deep learning approaches.

Abstract Accuracy is still the greatest challenge in the wireless sensor network localization efforts. Several diverse factors can give rise to localization errors. Modeling such diverse influencing factors to deliver a single, reasonably simple and practical solution is a difficult task. In order to address the problem of location inaccuracy, we propose a comparatively simple and ingenious approach, which is the simultaneous perturbation stochastic approximation (SPSA) localization engine. SPSA bypasses tedious modeling of the influencing factors where some of them are yet to be explored and random in nature. SPSA‐based localization estimates the non‐anchor node locations through minimizing the summation of estimated errors of all neighbors. However, the downside of SPSA is that it incurs errors in some specific relative neighborhood configurations often referred to as flip ambiguity. So, we further propose a solution to the flip ambiguity problem by implementing a constrained optimization with a penalty function method on the identified flip nodes. Most importantly, error propagation of the iterative localization algorithm is managed by incorporating a neighbor confidence matrix. We name this modified SPSA engine as simultaneous perturbation stochastic approximation by neighbor confidence (SPSA‐NC). Experimental results show that SPSA‐NC offers significantly better localization accuracy than its state‐of‐the‐art competitors, namely, simulated annealing and the ordinary SPSA. The SPSA‐NC program is available for downloading at http://www.dnagroup.org/SPSANC . Copyright © 2015 John Wiley & Sons, Ltd.

Localization precision remains active and open challenge in the area of wireless networks. For static network we develop model free approach of localization technique that by-passes the tedious modeling of diverse aspects to the contributing factor of localization errors, namely simultaneous perturbation stochastic approximation (SPSA) localization technique. The improved version of SPSA, simultaneous perturbation stochastic approximation by neighbor confidence (SPSA-NC) addresses error propagation of iterative localization controlled by incorporating a neighbor confidence matrix. The centralized SPSA and SPSA-NC does not scale well for the mobile environment due to the messaging requirements of repeated updates. We take distributed approaches to implement the aforementioned localization techniques for mobile devices by distributed simultaneous perturbation stochastic approximation (DSPSA) and distributed simultaneous perturbation stochastic approximation by neighbor confidence (DSPSA-NC) respectively, compare the results with the centroid (C) and weighted centroid (WC) localization techniques and show superiority of our methods.

Diversified opportunities (possible numerous applications) and challenges (resource constrained nodes) are contributing factors behind the extensive research in sensor networks. Continuous monitoring of the natural phenomenon is one of the major streams of the possible application in this arena. Sensing and monitoring of natural phenomenon involve dealing with correlated data in both spatial and temporal dimension. Aggregation technique plays a significant role by reducing the amount of data transmission in wireless sensor networks (WSN)as correlation is dominating in the real world. This reduction on the amount of data is vital due to the energy scarcity of the WSN. This paper presents a simple aggregation technique named smart aggregation (SAG) for the continuous-monitoring applications in WSNs. SAG maintains a tolerable deviation i.e. limited error in the aggregated data while compressing both spatially and temporarily. We present simulated results that rationalize the development of the protocol. The comparison is made with k-hop aggregation and CM-EDR algorithm in terms of energy efficiency showing the potential improvement gained by applying our aggregation scheme.

Abstract Optimized routing (from source to sink) in wireless sensor networks (WSN) constitutes one of the key design issues in prolonging the lifetime of battery‐limited sensor nodes. In this paper, we explore this optimization problem by considering different cost functions such as distance, remaining battery power, and link usage in selecting the next hop node among multiple candidates. Optimized selection is carried out through fuzzy inference system (FIS). Two differing algorithms are presented, namely optimized forwarding by fuzzy inference systems (OFFIS), and two‐layer OFFIS (2L‐OFFIS), that have been developed for flat and hierarchical networks, respectively. The proposed algorithms are compared with popular routing protocols that are considered as the closest counterparts such as minimum transmit energy (MTE) and low energy adaptive clustering hierarchy (LEACH). Simulation results demonstrate the superiority of the proposed algorithms in extending the WSN lifetime. Copyright © 2008 John Wiley & Sons, Ltd.

Routing protocols that can facilitate application- specific service guarantee in wireless sensor networks (WSN) constitute one of the key design objectives of current WSN research. Since energy-efficient routing protocols in literature do not offer a complete framework for service differentiation, a newer approach is warranted. Formulating such routing approach requires the adoption of different cost metrics that can parameterize the application-specific requirements. To this effect, this paper proposes an application-aware routing protocol (AARP) that considers battery power, data transaction reliability and end-to-end delay for service differentiation. Two mathematical models namely analytical hierarchical process (AHP) and grey relational analysis (GRA) are incorporated for intermediate node selection (ranking and subsequent selection based on local weight calculation) for data transaction purposes. As demonstrated by the simulation results, the proposed routing approach offers service configurability across a range of applications.

Network lifetime is the most important concern in designing a routing protocol for wireless sensor networks. To address the issue we have proposed optimized forwarding by fuzzy inference systems (OFFIS) for flat sensor networks [1]. The OFFIS protocol selects the best node from candidate nodes in the forwarding paths by favoring small hops, shortest path, maximum remaining battery power and link usage. The core strategy of OFFIS is to conserve as well as to distribute energy dissipation evenly in a decentralized manner. In this paper we compare OFFIS with the minimum transmit energy (MTE) technique and show that the lifetime can be improved notably.

Wireless sensor networks (WSNs) usually contain a large number of nodes typically with highly correlated collected data. To support large-scale wireless sensor network management and local data aggregation, hierarchical routing techniques can be regarded as superior to flat routing approaches. Low power consumption as well as smart way of distributing the load is crucial to the routing protocol design in order to attain elongated WSN lifetime. We have already proposed a distributed routing algorithm; optimized forwarding by fuzzy inference systems (OFFIS) for the flat networks, where the decision is based on the distance power and link uses. In this paper, we propose a two-layer OFFIS (2L-OFFIS) for environmental data collection in cluster-based sensor networks. Simulation results show that the network lifetime can be significantly elongated by utilizing the new protocol in hierarchical sensor networks