Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries

Wenjie Wang, Youngja Park, Taesung Lee, Ian Molloy, Pengfei Tang, Li Xiong


Abstract
Recent studies have shown that adversarial examples can be generated by applying small perturbations to the inputs such that the well- trained deep learning models will misclassify. With the increasing number of safety and security-sensitive applications of deep learn- ing models, the robustness of deep learning models has become a crucial topic. The robustness of deep learning models for health- care applications is especially critical because the unique characteristics and the high financial interests of the medical domain make it more sensitive to adversarial attacks. Among the modalities of medical data, the clinical summaries have higher risks to be attacked because they are generated by third-party companies. As few works studied adversarial threats on clinical summaries, in this work we first apply adversarial attack to clinical summaries of electronic health records (EHR) to show the text-based deep learning systems are vulnerable to adversarial examples. Secondly, benefiting from the multi-modality of the EHR dataset, we propose a novel defense method, MATCH (Multimodal feATure Consistency cHeck), which leverages the consistency between multiple modalities in the data to defend against adversarial examples on a single modality. Our experiments demonstrate the effectiveness of MATCH on a hospital readmission prediction task comparing with baseline methods.
Anthology ID:
2020.clinicalnlp-1.29
Volume:
Proceedings of the 3rd Clinical Natural Language Processing Workshop
Month:
November
Year:
2020
Address:
Online
Editors:
Anna Rumshisky, Kirk Roberts, Steven Bethard, Tristan Naumann
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
259–268
Language:
URL:
https://aclanthology.org/2020.clinicalnlp-1.29
DOI:
10.18653/v1/2020.clinicalnlp-1.29
Bibkey:
Cite (ACL):
Wenjie Wang, Youngja Park, Taesung Lee, Ian Molloy, Pengfei Tang, and Li Xiong. 2020. Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries. In Proceedings of the 3rd Clinical Natural Language Processing Workshop, pages 259–268, Online. Association for Computational Linguistics.
Cite (Informal):
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries (Wang et al., ClinicalNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.clinicalnlp-1.29.pdf
Video:
 https://slideslive.com/38939831