Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs

• URL: http://arxiv.org/abs/2603.20461v2
• Date: Tue, 24 Mar 2026 14:50:12 GMT
• Title: Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs
• Abstract summary: We study the inverse problem of determining the input images that get mapped to specific neural network classes.<n>In our forward pass method, we develop an inverse method based on a root-finding algorithm and the Jacobian with respect to the input image.<n>We show that our new methods are able to produce random-like input images that yield near perfect classification scores in all cases.
• Score: 2.507823797397027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network systems describe complex mappings that can be very difficult to understand. In this paper, we study the inverse problem of determining the input images that get mapped to specific neural network classes. Ultimately, we expect that these images contain recognizable features that are associated with their corresponding class classifications. We introduce two general methods for solving the inverse problem. In our forward pass method, we develop an inverse method based on a root-finding algorithm and the Jacobian with respect to the input image. In our backward pass method, we iteratively invert each layer, at the top. During the inversion process, we add random vectors sampled from the null-space of each linear layer. We demonstrate our new methods on both transformer architectures and sequential networks based on linear layers. Unlike previous methods, we show that our new methods are able to produce random-like input images that yield near perfect classification scores in all cases, revealing vulnerabilities in the underlying networks. Hence, we conclude that the proposed methods provide a more comprehensive coverage of the input image spaces that solve the inverse mapping problem.

Related papers

• BALI: Learning Neural Networks via Bayesian Layerwise Inference [6.7819070167076045]
  We introduce a new method for learning Bayesian neural networks, treating them as a stack of multivariate Bayesian linear regression models. The main idea is to infer the layerwise posterior exactly if we know the target outputs of each layer. We define these pseudo-targets as the layer outputs from the forward pass, updated by the backpropagated of the objective function.
  arXiv  Detail & Related papers  (2024-11-18T22:18:34Z)
• Understanding Neural Network Systems for Image Analysis using Vector Spaces and Inverse Maps [2.5979734944486648]
  We introduce techniques from Linear Algebra to model neural network layers as maps between signal spaces. We study invertible networks using vector spaces for computing input images that yield specific outputs.
  arXiv  Detail & Related papers  (2024-02-01T01:11:15Z)
• An Analytical Approach to Compute the Exact Preimage of Feed-Forward Neural Networks [0.0]
  This study is to give a method to compute the exact preimage of any Feed-Forward Neural Network with linear or piecewise linear activation functions for hidden layers. In contrast to other methods, this one is not returning a unique solution for a unique output but returns analytically the entire and exact preimage.
  arXiv  Detail & Related papers  (2022-02-28T18:12:04Z)
• Block shuffling learning for Deepfake Detection [9.180904212520355]
  Deepfake detection methods based on convolutional neural networks (CNN) have demonstrated high accuracy. These methods often suffer from decreased performance when faced with unknown forgery methods and common transformations. We propose a novel block shuffling regularization method to address this issue.
  arXiv  Detail & Related papers  (2022-02-06T17:16:46Z)
• A singular Riemannian geometry approach to Deep Neural Networks II. Reconstruction of 1-D equivalence classes [78.120734120667]
  We build the preimage of a point in the output manifold in the input space. We focus for simplicity on the case of neural networks maps from n-dimensional real spaces to (n - 1)-dimensional real spaces.
  arXiv  Detail & Related papers  (2021-12-17T11:47:45Z)
• Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion [90.65667807498086]
  This paper presents a zero-shot direct model inversion framework that recovers the input to the trained model given only the internal representation. We empirically show that modern classification models on ImageNet can, surprisingly, be inverted, allowing an approximate recovery of the original 224x224px images from a representation after more than 20 layers.
  arXiv  Detail & Related papers  (2021-07-13T18:01:43Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Image Restoration by Deep Projected GSURE [115.57142046076164]
  Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
  arXiv  Detail & Related papers  (2021-02-04T08:52:46Z)
• Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction [4.2476585678737395]
  We propose a general learning based framework for solving nonsmooth non image reconstruction problems. We show that the proposed is-efficient convergence state-of-the-art methods in an image problems in training.
  arXiv  Detail & Related papers  (2020-07-22T07:59:07Z)
• Neural Subdivision [58.97214948753937]
  This paper introduces Neural Subdivision, a novel framework for data-driven coarseto-fine geometry modeling. We optimize for the same set of network weights across all local mesh patches, thus providing an architecture that is not constrained to a specific input mesh, fixed genus, or category. We demonstrate that even when trained on a single high-resolution mesh our method generates reasonable subdivisions for novel shapes.
  arXiv  Detail & Related papers  (2020-05-04T20:03:21Z)
• Embedding Propagation: Smoother Manifold for Few-Shot Classification [131.81692677836202]
  We propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification. We empirically show that embedding propagation yields a smoother embedding manifold. We show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16% points.
  arXiv  Detail & Related papers  (2020-03-09T13:51:09Z)

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.