Return to Colloquia & Seminar listing
Tropical Geometric Approach to Robust Deep Neural Networks against Adversarial Attacks
Mathematics of Data & DecisionsSpeaker: | Ruriko Yoshida, Naval Postgraduate School (Monterey) |
Location: | 1025 PSEL |
Start time: | Tue, May 14 2024, 3:10PM |
We introduce a simple, easy to implement, and computationally efficient tropical convolutional neural network architecture that is robust against adversarial attacks. We exploit the tropical nature of piece-wise linear neural networks by embedding the data in the tropical projective torus in a single hidden layer which can be added to any model. We study the geometry of its decision boundary theoretically and show its robustness against adversarial attacks on image datasets using computational experiments. This is joint work with C. Teska, K. Pasque, K. Miura, and J. Huang.