Verification of Neural Networks: Specifying Global Robustness using Generative Models
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.
Code (2)
Similar Papers 제목 키워드 기반
Correctness Verification of Neural Networks
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
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…
modelCertifying Global Robustness for Deep Neural Networks
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
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 AttackUsing Z3 for Formal Modeling and Verification of FNN Global Robustness
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