# Network Inversion of Binarised Neural Nets

arXiv: https://arxiv.org/abs/2402.11995 · HTML: https://mlsanity.com/paper/2402.11995/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 4 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 2 of 2)

- [Verifying Properties of Binarized Deep Neural Networks](https://mlsanity.com/paper/1709.06662/) (2017)
- [Quantitative Verification of Neural Networks And its Security Applications](https://mlsanity.com/paper/1906.10395/) (2019)

## Built on by (most cited first, 11 of 11)

- [Network Inversion of Convolutional Neural Nets](https://mlsanity.com/paper/2407.18002/) (2024)
- [Shortcut Learning Susceptibility in Vision Classifiers](https://mlsanity.com/paper/2502.09150/) (2025)
- [Network Inversion for Generating Confidently Classified Counterfeits](https://mlsanity.com/paper/2503.20187/) (2025)
- [Network Inversion for Training-Like Data Reconstruction](https://mlsanity.com/paper/2410.16884/) (2024)
- [Network Inversion for Uncertainty-Aware Out-of-Distribution Detection](https://mlsanity.com/paper/2505.23448/) (2025)
- [Activation Matching for Explanation Generation](https://mlsanity.com/paper/2509.23051/) (2025)
- [Network Inversion and Its Applications](https://mlsanity.com/paper/2411.17777/) (2024)
- [EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation Matching](https://mlsanity.com/paper/2509.25686/) (2025)
- [TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection](https://mlsanity.com/paper/2512.00229/) (2025)
- [Med-CAM: Minimal Evidence for Explaining Medical Decision Making](https://mlsanity.com/paper/2604.13695/) (2026)
- [PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction](https://mlsanity.com/paper/2607.29378/) (2026)

## Abstract (arXiv)

While the deployment of neural networks, yielding impressive results, becomes more prevalent in various applications, their interpretability and understanding remain a critical challenge. Network inversion, a technique that aims to reconstruct the input space from the model's learned internal representations, plays a pivotal role in unraveling the black-box nature of input to output mappings in neural networks. In safety-critical scenarios, where model outputs may influence pivotal decisions, the integrity of the corresponding input space is paramount, necessitating the elimination of any extraneous "garbage" to ensure the trustworthiness of the network. Binarised Neural Networks (BNNs), characterized by binary weights and activations, offer computational efficiency and reduced memory requirements, making them suitable for resource-constrained environments. This paper introduces a novel approach to invert a trained BNN by encoding it into a CNF formula that captures the network's structure, allowing for both inference and inversion.