多轮对话中的个性化社会工程攻击：用于模拟与检测的LLM智能体
Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection
AI总结：
提出LLM智能体框架SE-VSim模拟多轮社会工程攻击，并基于超1000个对话提出SE-OmniGuard，利用受害者个性特征提供个性化防护与检测。
摘要：
对话智能体，特别是由大型语言模型（LLM）驱动的聊天机器人的快速发展，对社会媒体平台构成了社会工程（SE）攻击的重大风险。在多轮、基于聊天的交互中，SE检测比单实例检测复杂得多，因为这些对话具有动态性。缓解这一威胁的关键因素在于理解SE攻击机制，即攻击者如何利用漏洞，以及受害者的个性特征如何影响其易感性。在本工作中，我们提出一个LLM智能体框架SE-VSim，通过生成多轮对话来模拟SE攻击机制。我们建模具有不同个性特征的受害者智能体，以评估心理特征如何影响对操纵的易感性。利用一个包含超过1000个模拟对话的数据集，我们考察了攻击场景，其中对手伪装成招聘人员、资助机构和记者，试图提取敏感信息。基于此分析，我们提出一个概念验证SE-OmniGuard，通过利用受害者个性的先前知识、评估攻击策略并监控对话中的信息交换来识别潜在SE尝试，从而为用户提供个性化保护。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
