Haedong Jeong

Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling

Distilled gradient aggregation: Purify features for input attribution in the deep neural network

On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network

An unsupervised way to understand artifact generating internal units in generative neural networks

Example-based Methods to Explain the Internal Generative Mechanism of Deep Generative Neural Networks

Empirical Study of the Decision Region and Robustness in Deep Neural Networks

of KIISE

Automatic correction of internal units in generative neural networks