all AI news
How many perturbations break this model? Evaluating robustness beyond adversarial accuracy. (arXiv:2207.04129v2 [cs.LG] UPDATED)
Aug. 19, 2022, 1:11 a.m. | Raphael Olivier, Bhiksha Raj
stat.ML updates on arXiv.org arxiv.org
Robustness to adversarial attack is typically evaluated with adversarial
accuracy. This metric quantifies the number of points for which, given a threat
model, successful adversarial perturbations cannot be found. While essential,
this metric does not capture all aspects of robustness and in particular leaves
out the question of how many perturbations can be found for each point. In this
work we introduce an alternative approach, adversarial sparsity, which
quantifies how difficult it is to find a successful perturbation given both …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Data Analyst, Tableau
@ NTT DATA | Bengaluru, KA, IN
Junior Machine Learning Researcher
@ Weill Cornell Medicine | Doha, QA, 24144
Marketing Data Analytics Intern
@ Sloan | Franklin Park, IL, US, 60131
Senior Machine Learning Scientist
@ Adyen | Amsterdam
Data Engineer
@ Craft.co | Warsaw, Mazowieckie