all AI news
LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity. (arXiv:2207.13129v1 [cs.LG])
July 28, 2022, 1:10 a.m. | Martin Gubri, Maxime Cordy, Mike Papadakis, Yves Le Traon, Koushik Sen
cs.LG updates on arXiv.org arxiv.org
We propose transferability from Large Geometric Vicinity (LGV), a new
technique to increase the transferability of black-box adversarial attacks. LGV
starts from a pretrained surrogate model and collects multiple weight sets from
a few additional training epochs with a constant and high learning rate. LGV
exploits two geometric properties that we relate to transferability. First,
models that belong to a wider weight optimum are better surrogates. Second, we
identify a subspace able to generate an effective surrogate ensemble among this …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Analyst (H/F)
@ Business & Decision | Montpellier, France
Machine Learning Researcher
@ VERSES | Brighton, England, United Kingdom - Remote