An LLM Agent-based Framework for Whaling Countermeasures

2026-01-21

AI Summary

This study addresses the growing threat of high-precision generative AI-powered whaling attacks targeting senior university personnel, for which existing defenses lack personalization and contextual awareness. The work proposes the first defense framework based on large language model (LLM) agents, which constructs individualized vulnerability profiles by mining publicly available information, identifies high-risk scenarios, and generates contextually coherent, interpretable, and personalized defensive strategies. By innovatively deploying LLM agents for whaling protection tailored to academic staff, the approach demonstrates in preliminary experiments its ability to produce realistic risk assessments and strategy explanations aligned with actual professional contexts. These findings validate the framework’s feasibility while also highlighting key challenges for real-world deployment.

Technology Category

• Multiagent Systems: Adversarial Agents
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

With the spread of generative AI in recent years, attacks known as Whaling have become a serious threat. Whaling is a form of social engineering that targets important high-authority individuals within organizations and uses sophisticated fraudulent emails. In the context of Japanese universities, faculty members frequently hold positions that combine research leadership with authority within institutional workflows. This structural characteristic leads to the wide public disclosure of high-value information such as publications, grants, and detailed researcher profiles. Such extensive information exposure enables the construction of highly precise target profiles using generative AI. This raises concerns that Whaling attacks based on high-precision profiling by generative AI will become prevalent. In this study, we propose a Whaling countermeasure framework for university faculty members that constructs personalized defense profiles and uses large language model (LLM)-based agents. We design agents that (i) build vulnerability profiles for each target from publicly available information on faculty members, (ii) identify potential risk scenarios relevant to Whaling defense based on those profiles, (iii) construct defense profiles corresponding to the vulnerabilities and anticipated risks, and (iv) analyze Whaling emails using the defense profiles. Furthermore, we conduct a preliminary risk-assessment experiment. The results indicate that the proposed method can produce judgments accompanied by explanations of response policies that are consistent with the work context of faculty members who are Whaling targets. The findings also highlight practical challenges and considerations for future operational deployment and systematic evaluation.

Problem

• Whaling
• social engineering
• generative AI
• LLM agents
• cybersecurity

Innovation

• LLM agent
• Whaling defense
• personalized profiling
• social engineering countermeasure
• explainable response policy