2024/07/06 by Weimin Lyu, Lyu, Weimin, Zeyang Bi +4 · 2 citations
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Healthcare #Topic Modeling
paper · doi:10.48550/arxiv.2407.05213
openalex publication_date 2024/07/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31
The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their success, the potential vulnerabilities of these models remain largely unexplored. This paper delves into the realm of backdoor attacks on clinical language models, introducing an innovative attention-based backdoor attack method, BadCLM (Bad Clinical Language Models). This technique clandestinely embeds a backdoor within the models, causing them to produce incorrect predictions when a pre-defined trigger is present in inputs, while functioning accurately otherwise. We demonstrate the efficacy of BadCLM through an in-hospital mortality prediction task with MIMIC III dataset, showcasing its potential to compromise model integrity. Our findings illuminate a significant security risk in clinical decision support systems and pave the way for future endeavors in fortifying clinical language models against such vulnerabilities.