发表机构
Stony Brook University; The Graduate School（石溪大学; 研究生院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本论文针对NLP与VLMs面临的后门攻击安全威胁，研究了后门攻击的分析、检测与设计，并开发了适用于临床医学影像的多模态表示方法，助力可信AI与高效多模态学习。
AI 中文摘要
深度学习的最新进展显著提升了自然语言处理（NLP）和视觉-语言模型（VLMs）的能力，但这些进展也带来了更大的漏洞，尤其是后门攻击会构成严重的安全威胁。本论文针对可信AI与高效多模态表示学习的两个关键维度展开研究：（1）安全维度，分析、检测并设计NLP与VLMs中的后门攻击；（2）效率维度，开发适用于临床及医学影像应用的先进多模态表示方法。
英文摘要
Recent advances in deep learning have significantly enhanced the capabilities of Natural Language Processing (NLP) and Vision-Language Models (VLMs). However, these advancements come with increased vulnerabilities, notably through backdoor attacks that pose severe security threats. This thesis addresses two critical dimensions of Trustworthy AI and Efficient Multimodal Representation Learning: (1) security through analyzing, detecting, and designing backdoor attacks in NLP and VLMs, and (2) efficiency through advanced multimodal representation methods tailored for clinical and medical imaging applications.
CommentsPh.D. dissertation
