Jonghyun Chung
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This survey proposes a proactive, lifecycle-based framework, utilizing the C5 Interaction Model, to detect emerging adversarial synthetic narratives generated by Generative AI, moving beyond traditional reactive detection.
This survey proposes a proactive, lifecycle-based framework, utilizing the C5 Interaction Model, to detect emerging adversarial synthetic narratives generated by GenAI, moving beyond traditional reactive detection.
The paper proposes RAMP, a multi-corruption augmentation framework, which significantly improves the robustness and reliability of CT segmentation deep learning models when deployed in real-world, degraded clinical environments.
Papers
Pre-Deployment Robustness Stress Testing for CT Segmentation Systems Using Clinically Motivated Multi-Corruption Augmentation
The paper proposes RAMP, a multi-corruption augmentation framework, which significantly improves the robustness and reliability of CT segmentation deep learning models when deployed in real-world, deg…