A single prior network distilled from a 50-member self-supervised ensemble matches ensemble accuracy and robustness on HAR benchmarks at single-model inference cost.
On Norm-Agnostic Robustness of Adversarial Training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to increase robustness. In this paper, we propose a new attack to unveil an undesired property of the state-of-the-art adversarial training, that is it fails to obtain robustness against perturbations in $\ell_2$ and $\ell_\infty$ norms simultaneously. We discuss a possible solution to this issue and its limitations as well.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
A single prior network distilled from a 50-member self-supervised ensemble matches ensemble accuracy and robustness on HAR benchmarks at single-model inference cost.