Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models

Xu Han, Linghao Jin, Xuezhe Ma, Xiaofeng Liu


Abstract
Fine-tuning pre-trained Vision-Language Models (VLMs) has shown remarkable capabilities in medical image and textual depiction synergy. Nevertheless, many pre-training datasets are restricted by patient privacy concerns, potentially containing noise that can adversely affect downstream performance. Moreover, the growing reliance on multi-modal generation exacerbates this issue because of its susceptibility to adversarial attacks. To investigate how VLMs trained on adversarial noisy data perform on downstream medical tasks, we first craft noisy upstream datasets using multi-modal adversarial attacks. Through our comprehensive analysis, we unveil that moderate noise enhances model robustness and transferability, but increasing noise levels negatively impact downstream task performance. To mitigate this issue, we propose rectify adversarial noise (RAN) framework, a recipe designed to effectively defend adversarial attacks and rectify the influence of upstream noise during fine-tuning.
Anthology ID:
2024.findings-emnlp.633
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10784–10799
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.633
DOI:
Bibkey:
Cite (ACL):
Xu Han, Linghao Jin, Xuezhe Ma, and Xiaofeng Liu. 2024. Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10784–10799, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models (Han et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.633.pdf