[en] adversarial machine learning ; adversarial examples ; deep learning ; Transferability ; Loss Geometry
[en] 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\% points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples.
[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal]
