ScamPilot: Simulating Conversations with LLMs to Protect Against Online Scams

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hoffman, Owen, Peng, Kangze, Kamal, Sajid, You, Zehua, Venkatagiri, Sukrit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915762050957312
author Hoffman, Owen
Peng, Kangze
Kamal, Sajid
You, Zehua
Venkatagiri, Sukrit
author_facet Hoffman, Owen
Peng, Kangze
Kamal, Sajid
You, Zehua
Venkatagiri, Sukrit
contents Fraud continues to proliferate online, from phishing and ransomware to impersonation scams. Yet automated prevention approaches adapt slowly and may not reliably protect users from falling prey to new scams. To better combat online scams, we developed ScamPilot, a conversational interface that inoculates users against scams through simulation, dynamic interaction, and real-time feedback. ScamPilot simulates scams with two large language model-powered agents: a scammer and a target. Users must help the target defend against the scammer by providing real-time advice. Through a between-subjects study (N=150) with one control and three experimental conditions, we find that blending advice-giving with multiple choice questions significantly increased scam recognition (+8%) without decreasing wariness towards legitimate conversations. Users' response efficacy and change in self-efficacy was also 9% and 19% higher, respectively. Qualitatively, we find that users more frequently provided action-oriented advice over urging caution or providing emotional support. Overall, ScamPilot demonstrates the potential for inter-agent conversational user interfaces to augment learning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22426
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ScamPilot: Simulating Conversations with LLMs to Protect Against Online Scams
Hoffman, Owen
Peng, Kangze
Kamal, Sajid
You, Zehua
Venkatagiri, Sukrit
Human-Computer Interaction
Fraud continues to proliferate online, from phishing and ransomware to impersonation scams. Yet automated prevention approaches adapt slowly and may not reliably protect users from falling prey to new scams. To better combat online scams, we developed ScamPilot, a conversational interface that inoculates users against scams through simulation, dynamic interaction, and real-time feedback. ScamPilot simulates scams with two large language model-powered agents: a scammer and a target. Users must help the target defend against the scammer by providing real-time advice. Through a between-subjects study (N=150) with one control and three experimental conditions, we find that blending advice-giving with multiple choice questions significantly increased scam recognition (+8%) without decreasing wariness towards legitimate conversations. Users' response efficacy and change in self-efficacy was also 9% and 19% higher, respectively. Qualitatively, we find that users more frequently provided action-oriented advice over urging caution or providing emotional support. Overall, ScamPilot demonstrates the potential for inter-agent conversational user interfaces to augment learning.
title ScamPilot: Simulating Conversations with LLMs to Protect Against Online Scams
topic Human-Computer Interaction
url https://arxiv.org/abs/2601.22426