paper-with-me

Papers

Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity

2024-10-30 · Abulikemu Abuduweili, Changliu Liu

Ensuring neural network robustness is essential for the safe and reliable operation of robotic learning systems, especially in perception and decision-making tasks within real-world environments. This paper investigates the robustness of neural networks in perception systems, specifically examining their sensitivity to targeted, small-scale perturbations. We identify the Lipschitz constant as a key metric for quantifying and enhancing network robustness. We derive an analytical expression to compute the Lipschitz constant based on neural network architecture, providing a theoretical basis for estimating and improving robustness. Several experiments reveal the relationship between network design, the Lipschitz constant, and robustness, offering practical insights for developing safer, more robust robot learning systems.

📄 PDF Abstract BibTeX arXiv:2410.23382

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingSensitivity

Similar Papers 제목 키워드 기반

The Lipschitz Constant of Self-Attention

2020-06-08 · Hyunjik Kim, George Papamakarios, Andriy Mnih

Lipschitz constants of neural networks have been explored in various contexts in deep learning, such as provable adversarial robustness, estimating Wasserstein distance, stabilising training of GANs, and formulating inve…

Adversarial RobustnessLanguage Modelling

Scalable Lipschitz Estimation for CNNs

2024-03-27 · Yusuf Sulehman, Tingting Mu

Estimating the Lipschitz constant of deep neural networks is of growing interest as it is useful for informing on generalisability and adversarial robustness. Convolutional neural networks (CNNs) in particular, underpin …

Adversarial Robustness

Exactly Computing the Local Lipschitz Constant of ReLU Networks

2020-03-02 · NeurIPS 2020 12 · Matt Jordan, Alexandros G. Dimakis

The local Lipschitz constant of a neural network is a useful metric with applications in robustness, generalization, and fairness evaluation. We provide novel analytic results relating the local Lipschitz constant of non…

Fairness

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

2019-06-12 · NeurIPS 2019 12 · Mahyar Fazlyab, Alexander Robey, Hamed Hassani, Manfred Morari 외

Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforceme…

Reinforcement Learning

The robust way to stack and bag: the local Lipschitz way

2022-06-01 · Thulasi Tholeti, Sheetal Kalyani

Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness. We exploit this relationship to construct an ensemble of neural networks which not onl…

Adversarial Robustness