Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909777705041920 |
|---|---|
| author | Kumarage, Tharindu Johnson, Cameron Adams, Jadie Ai, Lin Kirchner, Matthias Hoogs, Anthony Garland, Joshua Hirschberg, Julia Basharat, Arslan Liu, Huan |
| author_facet | Kumarage, Tharindu Johnson, Cameron Adams, Jadie Ai, Lin Kirchner, Matthias Hoogs, Anthony Garland, Joshua Hirschberg, Julia Basharat, Arslan Liu, Huan |
| contents | The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based interactions is considerably more complex than single-instance detection due to the dynamic nature of these conversations. A critical factor in mitigating this threat is understanding the SE attack mechanisms through which SE attacks operate, specifically how attackers exploit vulnerabilities and how victims' personality traits contribute to their susceptibility. In this work, we propose an LLM-agentic framework, SE-VSim, to simulate SE attack mechanisms by generating multi-turn conversations. We model victim agents with varying personality traits to assess how psychological profiles influence susceptibility to manipulation. Using a dataset of over 1000 simulated conversations, we examine attack scenarios in which adversaries, posing as recruiters, funding agencies, and journalists, attempt to extract sensitive information. Based on this analysis, we present a proof of concept, SE-OmniGuard, to offer personalized protection to users by leveraging prior knowledge of the victims personality, evaluating attack strategies, and monitoring information exchanges in conversations to identify potential SE attempts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15552 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection Kumarage, Tharindu Johnson, Cameron Adams, Jadie Ai, Lin Kirchner, Matthias Hoogs, Anthony Garland, Joshua Hirschberg, Julia Basharat, Arslan Liu, Huan Cryptography and Security Computation and Language The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based interactions is considerably more complex than single-instance detection due to the dynamic nature of these conversations. A critical factor in mitigating this threat is understanding the SE attack mechanisms through which SE attacks operate, specifically how attackers exploit vulnerabilities and how victims' personality traits contribute to their susceptibility. In this work, we propose an LLM-agentic framework, SE-VSim, to simulate SE attack mechanisms by generating multi-turn conversations. We model victim agents with varying personality traits to assess how psychological profiles influence susceptibility to manipulation. Using a dataset of over 1000 simulated conversations, we examine attack scenarios in which adversaries, posing as recruiters, funding agencies, and journalists, attempt to extract sensitive information. Based on this analysis, we present a proof of concept, SE-OmniGuard, to offer personalized protection to users by leveraging prior knowledge of the victims personality, evaluating attack strategies, and monitoring information exchanges in conversations to identify potential SE attempts. |
| title | Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2503.15552 |