0

LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

The technique Large Geometric Vicinity (LGV) enhances the transferability of adversarial attacks by exploiting geometric properties of weight space in pretrained models.

Year
2022
Venue
arXiv 2022
Authors
5
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2207.13129ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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 wider optimum. Through extensive experiments, we show that LGV alone outperforms all (combinations of) four established test-time transformations by 1.8 to 59.9 percentage points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples.

Authors

5