# Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments

arXiv: https://arxiv.org/abs/2511.15165 · HTML: https://mlsanity.com/paper/2511.15165/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Distract Large Language Models for Automatic Jailbreak Attack](https://mlsanity.com/paper/2403.08424/) (2024)
- [Jailbreaking Large Language Models with Symbolic Mathematics](https://mlsanity.com/paper/2409.11445/) (2024)
- [Can MLLMs Understand the Deep Implication Behind Chinese Images?](https://mlsanity.com/paper/2410.13854/) (2024)
- [xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking](https://mlsanity.com/paper/2501.16727/) (2025)

## Abstract (arXiv)

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.