Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

1 code implementation • 5 Sep 2020 • Nilaksh Das, Haekyu Park, Zijie J. Wang, Fred Hohman, Robert Firstman, Emily Rogers, Duen Horng Chau

Deep neural networks (DNNs) are now commonly used in many domains.

Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning

no code implementations • 21 Jan 2020 • Nilaksh Das, Haekyu Park, Zijie J. Wang, Fred Hohman, Robert Firstman, Emily Rogers, Duen Horng Chau

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 applications.

Adversarial Attack