paper-with-me

홈 › Papers

On the Convergence of Certified Robust Training with Interval Bound Propagation

2022-03-16 · ICLR 2022 4 · Yihan Wang, Zhouxing Shi, Quanquan Gu, Cho-Jui Hsieh

Interval Bound Propagation (IBP) is so far the base of state-of-the-art methods for training neural networks with certifiable robustness guarantees when potential adversarial perturbations present, while the convergence of IBP training remains unknown in existing literature. In this paper, we present a theoretical analysis on the convergence of IBP training. With an overparameterized assumption, we analyze the convergence of IBP robust training. We show that when using IBP training to train a randomly initialized two-layer ReLU neural network with logistic loss, gradient descent can linearly converge to zero robust training error with a high probability if we have sufficiently small perturbation radius and large network width.

📄 PDF Abstract BibTeX arXiv:2203.08961

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks

2026-05-01 · Emma Andrews, Nahyeon Kim, Prabhat Mishra arxiv

Quantum machine learning is a promising field for efficiently learning features of a dataset to perform a specified task, such as classification. Interval bound propagation (IBP) is a popular certified training method in…

Quantum Machine LearningAdversarial Robustness

Universal Approximation with Certified Networks

2019-09-30 · ICLR 2020 1 · Maximilian Baader, Matthew Mirman, Martin Vechev

Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network that is both accurate and certifiably ro…

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

2019-06-14 · ICLR 2020 1 · Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal 외

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training …

Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation

2021-09-29 · ICLR 2022 4 · Colin Wei, J Zico Kolter

Deep equilibrium layers (DEQs) have demonstrated promising performance and are competitive with standard explicit models on many benchmarks. However, little is known about certifying robustness for these models. Inspired…

Understanding Certified Training with Interval Bound Propagation

2023-06-17 · Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev

As robustness verification methods are becoming more precise, training certifiably robust neural networks is becoming ever more relevant. To this end, certified training methods compute and then optimize an upper bound o…