PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

The article announces the release of PHANTOM, a large-scale open-source dataset consisting of 47,524 pre-generated adversarial samples specifically designed for evaluating vision-language models (VLMs). Covering 10 high-level categories and 55 subcategories of harmful intents, the dataset consolidates existing benchmarks and introduces new categories to enhance the evaluation of model robustness and safety. This resource aims to facilitate systematic assessments of VLMs under adversarial conditions, supporting researchers in fine-tuning attack-generation models and developing defensive strategies.