adversarial robustness 1dual teacher 1image classification 1information bottleneck 1knowledge distillation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers
Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi +1
The paper extends information bottleneck distillation by adding a clean‑trained teacher alongside a robust teacher, using cross‑layer attention to improve both clean accuracy and a…
cs.CG2024
Ironing the Graphs: Toward a Correct Geometric Analysis of Large-Scale Graphs
Saloua Naama, Kavé Salamatian, Francesco Bronzino
Graph embedding approaches attempt to project graphs into geometric entities, i.e, manifolds. The idea is that the geometric properties of the projected manifolds are helpful in th…