Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide
Abstract
Deep learning (DL) has demonstrated significant potential across various safety-critical applications, yet ensuring its robustness remains a key challenge. While adversarial robustness has been extensively studied in worst-case scenarios, probabilistic robustness (PR) offers a more practical perspective by quantifying the likelihood of failures under stochastic perturbations. This paper provides a concise yet comprehensive overview of PR, covering its formal definitions, evaluation and enhancement methods. We introduce a reformulated ''min-max'' optimisation framework for adversarial training specifically designed to improve PR. Furthermore, we explore the integration of PR verification evidence into system-level safety assurance, addressing challenges in translating DL model-level robustness to system-level claims. Finally, we highlight open research questions, including benchmarking PR evaluation methods, extending PR to generative AI tasks, and developing rigorous methodologies and case studies for system-level integration.
Cite
@article{arxiv.2502.14833,
title = {Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide},
author = {Xingyu Zhao},
journal= {arXiv preprint arXiv:2502.14833},
year = {2025}
}
Comments
This is a preprint of the following chapter: X. Zhao, Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide, published in the book Adversarial Example Detection and Mitigation Using Machine Learning, edited by Ehsan Nowroozi, Rahim Taheri, Lucas Cordeiro, 2025, Springer Nature. The final authenticated version will available online soon