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
Die Entdeckung von Online-Agent Social Engineering (SE) Betrügereien erfordert oft die Untersuchung von Website-Workflows, die Überprüfung von Ansprüchen gegenüber externen Quellen und die Verbindung von Beweisen auf mehreren Seiten. Bestehende Detektoren bieten begrenzte Unterstützung für diese Untersuchungen, so dass Analysten manuell sammeln und validieren Beweise, was unweigerlich verzögert die Entdeckung und nachfolgende Entfernung dieser Angriffe. Um diese Lücke zu beheben, präsentieren wir ReDence, ein offenes Quellen-Bewertungs-Hybrid-Framework für adaptive, evidenzbasierte Erkennung über verschiedene SE-Betrugskategorien. ReDence kombiniert zwei lokal gehostete Modelle mit ergänzenden Verantwortlichkeiten: ein fein-tuned
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange