References of "Fahmy, Hazem 50035776"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailHUDD: A tool to debug DNNs for safety analysis
Fahmy, Hazem UL; Pastore, Fabrizio UL; Briand, Lionel UL

in 2022 IEEE/ACM 44st International Conference on Software Engineering (2022, May)

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. HUDD ... [more ▼]

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. HUDD stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters error-inducing images whose results are due to common subsets of DNN neurons. The intent is for the generated clusters to group error-inducing images having common characteristics, that is, having a common root cause. HUDD identifies root causes by applying a clustering algorithm to matrices (i.e., heatmaps) capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters. Our empirical evaluation with DNNs from the automotive domain have shown that HUDD automatically identifies all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches. A demo video of HUDD is available at https://youtu.be/drjVakP7jdU. [less ▲]

Detailed reference viewed: 132 (29 UL)
Full Text
Peer Reviewed
See detailSupporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning
Fahmy, Hazem UL; Pastore, Fabrizio UL; Bagherzadeh, Mojtaba et al

in IEEE Transactions on Reliability (2021), 70(4), 1641-1657

Deep neural networks (DNNs) are increasingly im- portant in safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the ... [more ▼]

Deep neural networks (DNNs) are increasingly im- portant in safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components. We observe three major challenges with existing practices regarding DNNs in safety-critical systems: (1) scenarios that are underrepresented in the test set may lead to serious safety violation risks, but may, however, remain unnoticed; (2) char- acterizing such high-risk scenarios is critical for safety analysis; (3) retraining DNNs to address these risks is poorly supported when causes of violations are difficult to determine. 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. HUDD identifies root causes by applying a clustering algorithm to heatmaps capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters. We evaluated HUDD with DNNs from the automotive domain. HUDD was able to identify all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches. [less ▲]

Detailed reference viewed: 142 (32 UL)