Context-Aware RESTful API Framework for Real-Time Phishing Risk Mitigation Using Multidimensional Analytical Models

Phishing attacks represent a remarkable threat to the digital ecosystem, being especially vicious in fast-changing environments such as e commerce, social media, and online banking. The existing mitigation methods are either rule-based filtering, blacklisting, or feature extraction in isolation and fail to view the evolving contextual and behavioral dynamics of sophisticated phishing techniques. Such conventional models cannot adapt to changing environments, fail to look at sessionaware behavior, and consequently, respond in real time, at best. Thus, this study proposes a new RESTful Phishing Risk Mitigation Framework, a near-real-time, API-based architecture that detects phishing risks using context-aware set of intelligence. The model introduces five novel analytical methods capable of targeting very specific threat dimensions in HTTP-based interactions: Dynamic Meta-Behavioral Fusion (DMBF) calculates a behavioral risk vector by fusing metadata, device fingerprinting, and interaction metrics across sessions. Recursive Embedded Content Diffusion Analysis (RECDA) traces embedded resources recursively to evaluate deep-link phishing behavior using DOM simulations. Context-Aware Referrer Chain Validity (CRCV) examines the consistency of domain transitions and identifies semantic anomalies within referring chains. Temporal Entropy Sequencing Engine (TESE) analyzes time-series entropy of request patterns to detect botdriven or high-drift user behavior sets. Adaptive Client-Side Integrity Signal Aggregator (ACISA) captures passive client side anomalies including CSP violations and blocked script events for real-time integrity signals, increasing the final risk score. The layered framework improves detection accuracy, supports session continuity analysis, and allows for modular packages across various digital platforms. Experiments give an AUC of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\geq 0.93$</tex> while keeping false-positive rates below 4 %. This framework helps take a giant leap toward proactive phishing defense through behavioral-learning analysis, structural validation, and client-side introspection sets.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.