<ul><li>Randomized Smoothing (RS) is a promising technique for certified robustness in deep neural networks.</li><li>A new approach called SmOothed Multi-head Ensemble (SOME) is proposed, which uses multiple augmented heads with a cosine constraint inside a single DNN.</li><li>SOME achieves improved robustness with reduced computational costs compared to traditional ensemble methods of multiple DNNs.</li><li>Extensive experiments and discussions confirm the effectiveness and efficiency of SOME for certifiably-robust RS-based defense.</li></ul>

Multi-head Ensemble of Smoothed Classifiers for Certified Robustness

Discover more