Towards Verifying the Geometric Robustness of Large-scale Neural Networks

• URL: http://arxiv.org/abs/2301.12456v2
• Date: Thu, 30 Mar 2023 21:20:35 GMT
• Title: Towards Verifying the Geometric Robustness of Large-scale Neural Networks
• Authors: Fu Wang, Peipei Xu, Wenjie Ruan, Xiaowei Huang
• Abstract summary: Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation. This paper aims to verify the robustness of large-scale DNNs against the combination of multiple geometric transformations with a provable guarantee. We develop GeoRobust, a black-box optimisation analyser, for locating the worst-case combination of transformations.
• Score: 8.60992681271439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation. This paper aims to verify the robustness of large-scale DNNs against the combination of multiple geometric transformations with a provable guarantee. Given a set of transformations (e.g., rotation, scaling, etc.), we develop GeoRobust, a black-box robustness analyser built upon a novel global optimisation strategy, for locating the worst-case combination of transformations that affect and even alter a network's output. GeoRobust can provide provable guarantees on finding the worst-case combination based on recent advances in Lipschitzian theory. Due to its black-box nature, GeoRobust can be deployed on large-scale DNNs regardless of their architectures, activation functions, and the number of neurons. In practice, GeoRobust can locate the worst-case geometric transformation with high precision for the ResNet50 model on ImageNet in a few seconds on average. We examined 18 ImageNet classifiers, including the ResNet family and vision transformers, and found a positive correlation between the geometric robustness of the networks and the parameter numbers. We also observe that increasing the depth of DNN is more beneficial than increasing its width in terms of improving its geometric robustness. Our tool GeoRobust is available at https://github.com/TrustAI/GeoRobust.

Related papers

• NN-Former: Rethinking Graph Structure in Neural Architecture Representation [67.3378579108611]
  Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures.<n>We show that sibling nodes are pivotal while overlooked in previous research.<n>Our approach consistently achieves promising performance in both accuracy and latency prediction.
  arXiv  Detail & Related papers  (2025-07-01T15:46:18Z)
• Deep Learning as Ricci Flow [38.27936710747996]
  Deep neural networks (DNNs) are powerful tools for approximating the distribution of complex data. We show that the transformations performed by DNNs during classification tasks have parallels to those expected under Hamilton's Ricci flow. Our findings motivate the use of tools from differential and discrete geometry to the problem of explainability in deep learning.
  arXiv  Detail & Related papers  (2024-04-22T15:12:47Z)
• Convolutional Neural Networks on Manifolds: From Graphs and Back [122.06927400759021]
  We propose a manifold neural network (MNN) composed of a bank of manifold convolutional filters and point-wise nonlinearities. To sum up, we focus on the manifold model as the limit of large graphs and construct MNNs, while we can still bring back graph neural networks by the discretization of MNNs.
  arXiv  Detail & Related papers  (2022-10-01T21:17:39Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• Provable Defense Against Geometric Transformations [4.281091463408283]
  We propose the first provable defense for deterministic certified geometric robustness. We show that our framework consistently achieves state-of-the-art deterministic certified geometric robustness and clean accuracy. For the first time, we verify the geometric robustness of a neural network for the challenging, real-world setting of autonomous driving.
  arXiv  Detail & Related papers  (2022-07-22T16:40:03Z)
• B-cos Networks: Alignment is All We Need for Interpretability [136.27303006772294]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. A B-cos transform induces a single linear transform that faithfully summarises the full model computations. We show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets.
  arXiv  Detail & Related papers  (2022-05-20T16:03:29Z)
• MGNN: Graph Neural Networks Inspired by Distance Geometry Problem [28.789684784093048]
  Graph Neural Networks (GNNs) have emerged as a prominent research topic in the field of machine learning. In this paper, we propose a GNN model inspired by the congruent-inphilic property of the classifiers in the classification phase of GNNs. We extensively evaluate the effectiveness of our model through experiments conducted on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-01-31T04:15:42Z)
• Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need? [80.86819657126041]
  We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network [11.332580333969302]
  This work brings a new solution with a set of improvements, which increase the quantitative and qualitative understanding of depth maps. A graph convolutional network (GCN) can handle the convolution on non-Euclidean data and it can be applied to irregular image regions within a topological structure. Our method provided comparable and promising results with a high prediction accuracy of 89% on the publicly KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2021-12-13T16:46:25Z)
• Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty [91.0564497403256]
  We present a novel framework that involves probabilistic fusion between the two families of predictions during network training. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN and ScanNet datasets.
  arXiv  Detail & Related papers  (2021-04-16T17:59:06Z)
• EdgeNets:Edge Varying Graph Neural Networks [179.99395949679547]
  This paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs)
  arXiv  Detail & Related papers  (2020-01-21T15:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.