activity
20122019
most citedQuantitative Information Flow as Safety and Liveness Hyperproperties

2 citations · 2 across the 1 of their papers we have counts for

collaborators

6 papers

cs.SE2019

Engineering problems in machine learning systems

Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae

Fatal accidents are a major issue hindering the wide acceptance of safety-critical systems that employ machine learning and deep learning models, such as automated driving vehicles…

cs.CY2018

Open Problems in Engineering and Quality Assurance of Safety Critical Machine Learning Systems

Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae

Fatal accidents are a major issue hindering the wide acceptance of safety-critical systems using machine-learning and deep-learning models, such as automated-driving vehicles. Qual…

cs.LG2018

Runtime Monitoring Neuron Activation Patterns

Chih-Hong Cheng, Georg Nührenberg, Hirotoshi Yasuoka

For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runt…

cs.LG2018

Towards Dependability Metrics for Neural Networks

Chih-Hong Cheng, Georg Nührenberg, Chung-Hao Huang +2

Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for…

cs.SE2018

Quantitative Projection Coverage for Testing ML-enabled Autonomous Systems

Chih-Hong Cheng, Chung-Hao Huang, Hirotoshi Yasuoka

Systematically testing models learned from neural networks remains a crucial unsolved barrier to successfully justify safety for autonomous vehicles engineered using data-driven ap…

cs.CR20122 cited

Quantitative Information Flow as Safety and Liveness Hyperproperties

Hirotoshi Yasuoka, Tachio Terauchi

We employ Clarkson and Schneider's "hyperproperties" to classify various verification problems of quantitative information flow. The results of this paper unify and extend the prev…