Saved in:
Bibliographic Details
Main Authors: Vares, Fatemeh, Johnson, Brittany
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.17946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917998800928768
author Vares, Fatemeh
Johnson, Brittany
author_facet Vares, Fatemeh
Johnson, Brittany
contents Deep Neural Networks (DNNs) often rely on statistical correlations rather than causal reasoning, limiting their robustness and interpretability. While testing methods can identify failures, effective debugging and repair remain challenging. This paper explores causal inference as an approach primarily for DNN repair, leveraging causal debugging, counterfactual analysis, and structural causal models (SCMs) to identify and correct failures. We discuss in what ways these techniques support fairness, adversarial robustness, and backdoor mitigation by providing targeted interventions. Finally, we discuss key challenges, including scalability, generalization, and computational efficiency, and outline future directions for integrating causality-driven interventions to enhance DNN reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17946
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causality-Driven Neural Network Repair: Challenges and Opportunities
Vares, Fatemeh
Johnson, Brittany
Machine Learning
D.2.2; I.2.6
Deep Neural Networks (DNNs) often rely on statistical correlations rather than causal reasoning, limiting their robustness and interpretability. While testing methods can identify failures, effective debugging and repair remain challenging. This paper explores causal inference as an approach primarily for DNN repair, leveraging causal debugging, counterfactual analysis, and structural causal models (SCMs) to identify and correct failures. We discuss in what ways these techniques support fairness, adversarial robustness, and backdoor mitigation by providing targeted interventions. Finally, we discuss key challenges, including scalability, generalization, and computational efficiency, and outline future directions for integrating causality-driven interventions to enhance DNN reliability.
title Causality-Driven Neural Network Repair: Challenges and Opportunities
topic Machine Learning
D.2.2; I.2.6
url https://arxiv.org/abs/2504.17946