Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments
It addresses security challenges for academic institutions and researchers facing dynamic phishing threats, but appears incremental as it focuses on a specific domain without new methods.
The paper tackles the problem of phishing detection in academic environments using Multimodal Large Language Models (MLLMs) by introducing AdapT-Bench, a benchmark suite that addresses gaps in existing datasets, though no concrete performance numbers are provided.
The rapid proliferation of Multimodal Large Language Models (MLLMs) has introduced unprecedented security challenges, particularly in phishing detection within academic environments. Academic institutions and researchers are high-value targets, facing dynamic, multilingual, and context-dependent threats that leverage research backgrounds, academic collaborations, and personal information to craft highly tailored attacks. Existing security benchmarks largely rely on datasets that do not incorporate specific academic background information, making them inadequate for capturing the evolving attack patterns and human-centric vulnerability factors specific to academia. To address this gap, we present AdapT-Bench, a unified methodological framework and benchmark suite for systematically evaluating MLLM defense capabilities against dynamic phishing attacks in academic settings.