Newest papers

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

Jaishnoor Kaur, Josef Horacek, Ian Waskom, Sayak Saha Roy · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30963 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Detectar fraudes de engenharia social on-line (SE) frequentemente requer exame de fluxos de trabalho do site, verificação de reivindicações contra fontes externas e conexão de evidências em várias páginas. Os detectores existentes fornecem suporte limitado para essas investigações, deixando os analistas recolherem e validarem as evidências manualmente, o que inevitavelmente retarda a detecção e a remoção subsequente desses ataques. Para resolver essa lacuna, apresentamos o ReDence, um framework híbrido de evidências de código aberto para a detecção adaptativa e baseada em evidências em várias categorias de fraudes SE. O ReDence combina dois modelos hospedados localmente com responsabilidades complementares: um Investigador de agentes multimodal finamente ajustado (Qwen3.5-4B) que realiza

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 responsibilities: a fine-tuned multimodal agentic Investigator (Qwen3.5-4B) that performs investigative planning, evidence interpretation, and reporting, and a specialized Decider (Tev1) that handles binary and multiple-choice tasks, including browser-action selection, evidence assessment, and decisions about whether to continue an investigation. By delegating discrete decisions to a specialized model, ReDence reduces reliance on lengthy language-model responses, while preserving the reasoning capabilities required for complex investigations. Our evaluation demonstrates that ReDence achieves 96\% accuracy in detecting scams across twelve SE scam categories, substantially outperforming existing detectors while being at least four times faster than comparable agentic models without compromising investigative depth. ReDence also produces structured, evidence-grounded reports that document investigative actions, supporting and contradictory evidence, and collected artifacts, which allow analysts to independently audit detection decisions and utilize the collected evidence to support subsequent mitigation and takedown efforts.

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

Topics: Audit, Computer science, Data science, Social engineering (security), Computer security, Internet privacy

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