22 citations · 62 across the 50 of their papers we have counts for
12 papers · 1 filter
Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
Zhiyuan Peng, Zihan Ye, Shreyank N Gowda +3
Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classificati…
Performance is not All You Need: Sustainability Considerations for Algorithms
Xiang Li, Chong Zhang, Hongpeng Wang +3
This work focuses on the high carbon emissions generated by deep learning model training, specifically addressing the core challenge of balancing algorithm performance and energy c…
Prototype-Enhanced Confidence Modeling for Cross-Modal Medical Image-Report Retrieval
Shreyank N Gowda, Xiaobo Jin, Christian Wagner
In cross-modal retrieval tasks, such as image-to-report and report-to-image retrieval, accurately aligning medical images with relevant text reports is essential but challenging du…
Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known a…
Distribution-Based Masked Medical Vision-Language Model Using Structured Reports
Shreyank N Gowda, Ruichi Zhang, Xiao Gu +2
Medical image-language pre-training aims to align medical images with clinically relevant text to improve model performance on various downstream tasks. However, existing models of…
Sensing Cardiac Health Across Scenarios and Devices: A Multi-Modal Foundation Model Pretrained on Heterogeneous Data from 1.7 Million Individuals
Xiao Gu, Wei Tang, Jinpei Han +10
Cardiac biosignals, such as electrocardiograms (ECG) and photoplethysmograms (PPG), are of paramount importance for the diagnosis, prevention, and management of cardiovascular dise…