Guardado en:
Detalles Bibliográficos
Autores principales: Sehwag, Udari Madhushani, Patel, Kelly, Mosca, Francesca, Ravi, Vineeth, Staddon, Jessica
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.13893
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915395741417472
author Sehwag, Udari Madhushani
Patel, Kelly
Mosca, Francesca
Ravi, Vineeth
Staddon, Jessica
author_facet Sehwag, Udari Madhushani
Patel, Kelly
Mosca, Francesca
Ravi, Vineeth
Staddon, Jessica
contents Despite the importance of developing generative AI models that can effectively resist scams, current literature lacks a structured framework for evaluating their vulnerability to such threats. In this work, we address this gap by constructing a benchmark based on the FINRA taxonomy and systematically assessing Large Language Models' (LLMs') vulnerability to a variety of scam tactics. First, we incorporate 37 well-defined base scam scenarios reflecting the diverse scam categories identified by FINRA taxonomy, providing a focused evaluation of LLMs' scam detection capabilities. Second, we utilize representative proprietary (GPT-3.5, GPT-4) and open-source (Llama) models to analyze their performance in scam detection. Third, our research provides critical insights into which scam tactics are most effective against LLMs and how varying persona traits and persuasive techniques influence these vulnerabilities. We reveal distinct susceptibility patterns across different models and scenarios, underscoring the need for targeted enhancements in LLM design and deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13893
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can LLMs be Scammed? A Baseline Measurement Study
Sehwag, Udari Madhushani
Patel, Kelly
Mosca, Francesca
Ravi, Vineeth
Staddon, Jessica
Cryptography and Security
Despite the importance of developing generative AI models that can effectively resist scams, current literature lacks a structured framework for evaluating their vulnerability to such threats. In this work, we address this gap by constructing a benchmark based on the FINRA taxonomy and systematically assessing Large Language Models' (LLMs') vulnerability to a variety of scam tactics. First, we incorporate 37 well-defined base scam scenarios reflecting the diverse scam categories identified by FINRA taxonomy, providing a focused evaluation of LLMs' scam detection capabilities. Second, we utilize representative proprietary (GPT-3.5, GPT-4) and open-source (Llama) models to analyze their performance in scam detection. Third, our research provides critical insights into which scam tactics are most effective against LLMs and how varying persona traits and persuasive techniques influence these vulnerabilities. We reveal distinct susceptibility patterns across different models and scenarios, underscoring the need for targeted enhancements in LLM design and deployment.
title Can LLMs be Scammed? A Baseline Measurement Study
topic Cryptography and Security
url https://arxiv.org/abs/2410.13893