paper-with-me

Papers

Debate-Driven Multi-Agent LLMs for Phishing Email Detection

2025-03-27 · Ngoc Tuong Vy Nguyen, Felix D Childress, Yunting Yin

Phishing attacks remain a critical cybersecurity threat. Attackers constantly refine their methods, making phishing emails harder to detect. Traditional detection methods, including rule-based systems and supervised machine learning models, either rely on predefined patterns like blacklists, which can be bypassed with slight modifications, or require large datasets for training and still can generate false positives and false negatives. In this work, we propose a multi-agent large language model (LLM) prompting technique that simulates debates among agents to detect whether the content presented on an email is phishing. Our approach uses two LLM agents to present arguments for or against the classification task, with a judge agent adjudicating the final verdict based on the quality of reasoning provided. This debate mechanism enables the models to critically analyze contextual cue and deceptive patterns in text, which leads to improved classification accuracy. The proposed framework is evaluated on multiple phishing email datasets and demonstrate that mixed-agent configurations consistently outperform homogeneous configurations. Results also show that the debate structure itself is sufficient to yield accurate decisions without extra prompting strategies.

📄 PDF Abstract BibTeX arXiv:2503.22038

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

2025-09-27 · Binwei Yao, Chao Shang, Wanyu Du, Jianfeng He 외 arxiv

Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to …

Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning

2025-10-08 · Xuhang Chen, Zhifan Song, Deyi Ji, Shuo Gao 외 arxiv

Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to d…

SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction

2026-06-03 · Kenfeng Huang, Yi Cai, Xin Wu, Zikun Deng 외 arxiv

Zero-shot information extraction (IE) with large language models (LLMs) has attracted increasing attention due to its flexibility in adapting to new schemas and domains without task-specific training. Existing approaches…

Information Extraction

Next-Generation Phishing: How LLM Agents Empower Cyber Attackers

2024-11-21 · Khalifa Afane, Wenqi Wei, Ying Mao, Junaid Farooq 외

The escalating threat of phishing emails has become increasingly sophisticated with the rise of Large Language Models (LLMs). As attackers exploit LLMs to craft more convincing and evasive phishing emails, it is crucial …

Data Augmentation

A Theory of Post-hoc Debate Judgement

2026-08-19 · Xiang Yin, Adam Dejl, Antonio Rago, Lihu Chen 외 arxiv

Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and user engagement. For example, LLM-empowered agents may debate internally (with themselves) …