Robert Firstman
YOU?
Author Swipe
View article: Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks Open
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 a model into making incorrect predictions. Despite signifi…
View article: Massif: Interactive Interpretation of Adversarial Attacks on Deep\n Learning
Massif: Interactive Interpretation of Adversarial Attacks on Deep\n Learning Open
Deep neural networks (DNNs) are increasingly powering high-stakes\napplications such as autonomous cars and healthcare; however, DNNs are often\ntreated as "black boxes" in such applications. Recent research has also\nrevealed that DNNs ar…