# Revisiting the Robust Generalization of Adversarial Prompt Tuning

arXiv: https://arxiv.org/abs/2405.11154 · HTML: https://mlsanity.com/paper/2405.11154/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 18 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Built on by (most cited first, 3 of 3)

- [Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models](https://mlsanity.com/paper/2503.12874/) (2025)
- [Generalizable Prompt Learning of CLIP: A Brief Overview](https://mlsanity.com/paper/2503.01263/) (2025)
- [Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners](https://mlsanity.com/paper/2505.14042/) (2025)

## Abstract (arXiv)

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms generally adopt prompt learning strategies for adversarial fine-tuning to improve the adversarial robustness of the pre-trained model while keeping the efficiency of adapting to downstream tasks. Such a setup leads to the problem of over-fitting which impedes further improvement of the model's generalization capacity on both clean and adversarial examples. In this work, we propose an adaptive Consistency-guided Adversarial Prompt Tuning (i.e., CAPT) framework that utilizes multi-modal prompt learning to enhance the alignment of image and text features for adversarial examples and leverage the strong generalization of pre-trained CLIP to guide the model-enhancing its robust generalization on adversarial examples while maintaining its accuracy on clean ones. We also design a novel adaptive consistency objective function to balance the consistency of adversarial inputs and clean inputs between the fine-tuning model and the pre-trained model. We conduct extensive experiments across 14 datasets and 4 data sparsity schemes (from 1-shot to full training data settings) to show the superiority of CAPT over other state-of-the-art adaption methods. CAPT demonstrated excellent performance in terms of the in-distribution performance and the generalization under input distribution shift and across datasets.