LGCRCVMLJul 26, 2022

LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

arXiv:2207.13129v169 citationsh-index: 67
Originality Highly original
AI Analysis

This addresses the challenge of creating more effective adversarial attacks for security testing in machine learning, representing a novel approach rather than an incremental improvement.

The paper tackles the problem of improving the transferability of black-box adversarial attacks by proposing LGV, a technique that leverages geometric properties of the weight space, resulting in performance gains of 1.8 to 59.9 percentage points over existing methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes