paper-with-me

홈 › Papers

Verification of Neural Networks: Specifying Global Robustness using Generative Models

2019-10-11 · Nathanaël Fijalkow, Mohit Kumar Gupta

The success of neural networks across most machine learning tasks and the persistence of adversarial examples have made the verification of such models an important quest. Several techniques have been successfully developed to verify robustness, and are now able to evaluate neural networks with thousands of nodes. The main weakness of this approach is in the specification: robustness is asserted on a validation set consisting of a finite set of examples, i.e. locally. We propose a notion of global robustness based on generative models, which asserts the robustness on a very large and representative set of examples. We show how this can be used for verifying neural networks. In this paper we experimentally explore the merits of this approach, and show how it can be used to construct realistic adversarial examples.

📄 PDF Abstract BibTeX arXiv:1910.05018

Code (2)

mohitiitb/NeuralNetworkVerification_GlobalRobustness 공식 구현 tf
mohitiitb/DummyRepo tf

Similar Papers 제목 키워드 기반

Correctness Verification of Neural Networks

2019-06-03 · Yichen Yang, Martin Rinard

We present a novel framework for specifying and verifying correctness globally for neural networks on perception tasks. Most previous works on neural network verification for perception tasks focus on robustness verifica…

Verification of Generative-Model-Based Visual Transformations

2019-09-25 · Matthew Mirman, Timon Gehr, Martin Vechev

Generative networks are promising models for specifying visual transformations. Unfortunately, certification of generative models is challenging as one needs to capture sufficient non-convexity so to produce precise boun…

model

Certifying Global Robustness for Deep Neural Networks

2024-05-31 · You Li, Guannan Zhao, Shuyu Kong, Yunqi He 외

A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systema…

Global Robustness Verification Networks

2020-06-08 · Weidi Sun, Yuteng Lu, Xiyue Zhang, Zhanxing Zhu 외

The wide deployment of deep neural networks, though achieving great success in many domains, has severe safety and reliability concerns. Existing adversarial attack generation and automatic verification techniques cannot…

Adversarial Attack

Using Z3 for Formal Modeling and Verification of FNN Global Robustness

2023-04-20 · Yihao Zhang, Zeming Wei, Xiyue Zhang, Meng Sun

While Feedforward Neural Networks (FNNs) have achieved remarkable success in various tasks, they are vulnerable to adversarial examples. Several techniques have been developed to verify the adversarial robustness of FNNs…

Adversarial Robustness