Saved in:
Bibliographic Details
Main Authors: Suhail, Pirzada, Chakraborty, Supratik, Sethi, Amit
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.11995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909111498571776
author Suhail, Pirzada
Chakraborty, Supratik
Sethi, Amit
author_facet Suhail, Pirzada
Chakraborty, Supratik
Sethi, Amit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11995
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Network Inversion of Binarised Neural Nets
Suhail, Pirzada
Chakraborty, Supratik
Sethi, Amit
Machine Learning
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.
title Network Inversion of Binarised Neural Nets
topic Machine Learning
url https://arxiv.org/abs/2402.11995