Search Results for author:
Found 6 papers, 4 papers with code
Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches
In our previous work, we proposed a white-box approach (HUDD) and a black-box approach (SAFE) to automatically characterize DNN failures.
HUDD: A tool to debug DNNs for safety analysis
We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN.
Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i. e., erroneous outputs) observed during testing.
Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering
Experimental results show the superior ability of SAFE in identifying different root causes of DNN errors based on case studies in the automotive domain.
Mutation Analysis for Cyber-Physical Systems: Scalable Solutions and Results in the Space Domain
On-board embedded software developed for spaceflight systems (space software) must adhere to stringent software quality assurance procedures.
Software Engineering
Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning
To address these problems in the context of DNNs analyzing images, we propose HUDD, an approach that automatically supports the identification of root causes for DNN errors.
