Výsledky vyhledávání - "Liu, Jiangchao"

Report

Hybrid Inlining: A Compositional and Context Sensitive Static Analysis Framework

Autor: Liu, Jiangchao, Liu, Jierui, Di, Peng, Wu, Diyu, Zheng, Hengjie, Liu, Alex, Xue, Jingling

Context sensitivity is essential for achieving the precision in inter-procedural static analysis. To be (fully) context sensitive, top-down analysis needs to fully inline all statements of the callees at each callsite, leading to statement explosion.

Externí odkaz: http://arxiv.org/abs/2210.14436

Zobrazit plný text záznamu

Report

Input Validation for Neural Networks via Runtime Local Robustness Verification

Autor: Liu, Jiangchao, Chen, Liqian, Mine, Antoine, Wang, Ji

Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs

Externí odkaz: http://arxiv.org/abs/2002.03339

Zobrazit plný text záznamu

Dissertation/ Thesis

Static analysis on numeric and structural properties of array contents

Autor: Liu, Jiangchao

Dans cette thèse, nous étudions l'analyse statique par interprétation abstraites de programmes manipulant des tableaux, afin d'inférer des propriétés sur les valeurs numériques et les structures de données qui y sont stockées. Les tableaux s

Externí odkaz: http://www.theses.fr/2018PSLEE046/document

Zobrazit plný text záznamu

Report

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification

Autor: Li, Jianlin, Yang, Pengfei, Liu, Jiangchao, Chen, Liqian, Huang, Xiaowei, Zhang, Lijun

Deep neural networks (DNNs) have been shown lack of robustness for the vulnerability of their classification to small perturbations on the inputs. This has led to safety concerns of applying DNNs to safety-critical domains. Several verification appro

Externí odkaz: http://arxiv.org/abs/1902.09866

Zobrazit plný text záznamu