LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

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.

Cite

Text

Gubri et al. "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19772-7_35

Markdown

[Gubri et al. "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/gubri2022eccv-lgv/) doi:10.1007/978-3-031-19772-7_35

BibTeX

@inproceedings{gubri2022eccv-lgv,
  title     = {{LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity}},
  author    = {Gubri, Martin and Cordy, Maxime and Papadakis, Mike and Le Traon, Yves and Sen, Koushik},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-19772-7_35},
  url       = {https://mlanthology.org/eccv/2022/gubri2022eccv-lgv/}
}