SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Classification XOR KNN Accuracy 93.057 # 1
Classification XOR LDA Accuracy 77.2217 # 4
Classification XOR CART Accuracy 92.8179 # 3
Classification XOR RF Accuracy 92.962 # 2

Methods used in the Paper


METHOD TYPE
Dense Connections
Feedforward Networks
Feedforward Network
Feedforward Networks
Gaussian Process
Non-Parametric Classification
SVM
Non-Parametric Classification