Newest papers

ReDence: A Hybrid Agentic and Decision-Model Framework for Rapid, Evidence-Grounded Detection of Modern Social Engineering Scams

Jaishnoor Kaur, Josef Horáček, Ian Waskom, Sayak Saha Roy · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30963 · open-access PDF

French

La détection de fraudes en ingénierie sociale en ligne (SE) nécessite souvent l'examen des flux de travail du site, la vérification des revendications contre des sources externes et la connexion des preuves sur plusieurs pages. Les détecteurs existants fournissent un soutien limité à ces enquêtes, laissant les analystes à recueillir et à valider manuellement les preuves, ce qui retarde inévitablement la détection et la suppression ultérieure de ces attaques. Pour remédier à cette lacune, nous présentons ReDence, un cadre hybride open-source pour la détection adaptative et fondée sur des preuves sur diverses catégories de fraudes SE.

Machine translation (Meta M2M100); the English original follows.

Abstract

Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing detectors provide limited support for these investigations, leaving analysts to manually gather and validate evidence, which inevitably delays detection and subsequent takedown of these attacks. To address this gap, we present ReDence, an open-source hybrid framework for adaptive, evidence-grounded detection across diverse SE scam categories. ReDence combines two locally hosted models with complementary res

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30963, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange