Kristina Nikolić (@nkristina.bsky.social)

Ensemble Everything Everywhere is a defense against adversarial examples that people got quite exited about a few months ago (in particular, the defense causes "perceptually aligned" gradients just like adversarial training) Unfortunately, we show it's not robust... arxiv.org/abs/2411.14834

loading . . .

Gradient Masking All-at-Once: Ensemble Everything Everywhere Is Not Robust Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations... https://arxiv.org/abs/2411.14834