341 citations · 472 across the 21 of their papers we have counts for
4 papers · 1 filter
Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries
Haekyu Park, Seongmin Lee, Benjamin Hoover +7
We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training. Our work add…
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks
Nilaksh Das, Haekyu Park, Zijie J. Wang +4
Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool…
Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning
Nilaksh Das, Haekyu Park, Zijie J. Wang +4
Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such appl…
NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions
Haekyu Park, Fred Hohman, Duen Horng Chau
As deep neural networks are increasingly used in solving high-stake problems, there is a pressing need to understand their internal decision mechanisms. Visualization has helped ad…