# Network Inversion for Generating Confidently Classified Counterfeits

arXiv: https://arxiv.org/abs/2503.20187 · HTML: https://mlsanity.com/paper/2503.20187/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Generating Adversarial Examples with Adversarial Networks](https://mlsanity.com/paper/1801.02610/) (2018)
- [Model Inversion Networks for Model-Based Optimization](https://mlsanity.com/paper/1912.13464/) (2019)
- [Robust Models are less Over-Confident](https://mlsanity.com/paper/2210.05938/) (2022)
- [Autoinverse: Uncertainty Aware Inversion of Neural Networks](https://mlsanity.com/paper/2208.13780/) (2022)
- [Network Inversion of Binarised Neural Nets](https://mlsanity.com/paper/2402.11995/) (2024)
- [Network Inversion of Convolutional Neural Nets](https://mlsanity.com/paper/2407.18002/) (2024)

## Built on by (most cited first, 2 of 2)

- [Network Inversion for Uncertainty-Aware Out-of-Distribution Detection](https://mlsanity.com/paper/2505.23448/) (2025)
- [TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection](https://mlsanity.com/paper/2512.00229/) (2025)

## Abstract (arXiv)

In vision classification, generating inputs that elicit confident predictions is key to understanding model behavior and reliability, especially under adversarial or out-of-distribution (OOD) conditions. While traditional adversarial methods rely on perturbing existing inputs to fool a model, they are inherently input-dependent and often fail to ensure both high confidence and meaningful deviation from the training data. In this work, we extend network inversion techniques to generate Confidently Classified Counterfeits (CCCs), synthetic samples that are confidently classified by the model despite being significantly different from the training distribution and independent of any specific input. We alter inversion technique by replacing soft vector conditioning with one-hot class conditioning and introducing a Kullback-Leibler divergence loss between the one-hot label and the classifier's output distribution. CCCs offer a model-centric perspective on confidence, revealing that models can assign high confidence to entirely synthetic, out-of-distribution inputs. This challenges the core assumption behind many OOD detection techniques based on thresholding prediction confidence, which assume that high-confidence outputs imply in-distribution data, and highlights the need for more robust uncertainty estimation in safety-critical applications.