×
Oct 3, 2020 · Recent studies show that it is possible to achieve fast Adversarial Training by performing a single-step attack with random initialization.
A new initialization strategy, backward smoothing, is proposed to ad- dress this issue and significantly improves both stability and model robustness over ...
Jun 28, 2022 · In order to further improve the robustness-efficiency trade-off of fast robust training techniques, we propose a new initialization strat- egy, ...
This work develops a new understanding towards Fast Adversarial Training, by viewing random initialization as performing randomized smoothing for better ...
Sep 13, 2024 · A new initialization strategy, backward smoothing, is proposed to address this issue and significantly improves both stability and model ...
This is the official code for our paper Efficient Robust Training via Backward Smoothing (aceepted by AAAI'2022) by Jinghui Chen (PSU), Yu Cheng (Microsoft) ...
Oct 6, 2020 · Paper: Efficient Robust Training via Backward Smoothing https://arxiv.org/abs/2010.01278 Venue: {if applicable, the venue where the paper ...
We propose a new method called bridged adversarial training that mitigates the negative effect by bridging the gap between clean and adversarial examples.
May 1, 2024 · This chapter explores the foundational concept of robustness in Machine Learning (ML) and its integral role in establishing trustworthiness in Artificial ...