paint-brush
Adversarial Training in Multi-Exit Networks: Proposed NEO-KD Algorithm and Problem Setupby@textmodels

Adversarial Training in Multi-Exit Networks: Proposed NEO-KD Algorithm and Problem Setup

tldt arrow

Too Long; Didn't Read

This section outlines adversarial training for multi-exit networks, focusing on three attack methods: single, max-average, and average attacks. The generated adversarial examples target different submodels, but the correlation among submodels can increase adversarial transferability, which is a challenge in multi-exit network robustness.
featured image - Adversarial Training in Multi-Exit Networks: Proposed NEO-KD Algorithm and Problem Setup
Writings, Papers and Blogs on Text Models HackerNoon profile picture