Towards Dependability Metrics for Neural Networks
Not on the map. Why?
Abstract (arXiv)
Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important NN dependability attributes. We address this challenge by proposing a number of NN-specific and efficiently computable metrics for measuring NN dependability attributes including robustness, interpretability, completeness, and correctness.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 6; 2023: 1; 2024: 3; 2025: 0; 2026: 1.
13 papers.
Sort:
- 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
- 2022Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddingscited by 7
- 2024Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Studycited by 5
- 2023PEM: Perception Error Model for Virtual Testing of Autonomous Vehiclescited by 4
- 2022Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communicationscited by 3
- 2021Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domainscited by 2
- 2022A causal model of safety assurance for machine learningcited by 2
- 2024A Survey of Neural Network Robustness Assessment in Image Recognitioncited by 2
- 2022Backdoor Mitigation in Deep Neural Networks via Strategic Retrainingcited by 1
- 2024Outline of an Independent Systematic Blackbox Test for ML-based Systemscited by 1
- 2022Safe AI -- How is this Possible?cited by 0
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activitiescited by 0
- 2026Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems21 Sep 2026
- 2024Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study31 May 2024
- 2024A Survey of Neural Network Robustness Assessment in Image Recognition12 Apr 2024
- 2024Outline of an Independent Systematic Blackbox Test for ML-based Systems30 Jan 2024
- 2023PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles23 Feb 2023
- 2022Backdoor Mitigation in Deep Neural Networks via Strategic Retraining14 Dec 2022
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activities30 Sep 2022
- 2022Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communications30 Mar 2022
- 2022Safe AI -- How is this Possible?25 Jan 2022
- 2022A causal model of safety assurance for machine learning14 Jan 2022
- 2022Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings3 Jan 2022
- 2021Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domains17 Aug 2021
1 more
- 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
- 2022Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddingscited by 7
- 2024Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Studycited by 5
- 2023PEM: Perception Error Model for Virtual Testing of Autonomous Vehiclescited by 4
- 2022Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communicationscited by 3
- 2021Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domainscited by 2
- 2022A causal model of safety assurance for machine learningcited by 2
- 2024A Survey of Neural Network Robustness Assessment in Image Recognitioncited by 2
- 2022Backdoor Mitigation in Deep Neural Networks via Strategic Retrainingcited by 1
- 2024Outline of an Independent Systematic Blackbox Test for ML-based Systemscited by 1
- 2022Safe AI -- How is this Possible?cited by 0
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activitiescited by 0
12 most cited of 13 All 13 (JSON)
- 2026Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems21 Sep 2026
- 2024Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study31 May 2024
- 2024A Survey of Neural Network Robustness Assessment in Image Recognition12 Apr 2024
- 2024Outline of an Independent Systematic Blackbox Test for ML-based Systems30 Jan 2024
- 2023PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles23 Feb 2023
- 2022Backdoor Mitigation in Deep Neural Networks via Strategic Retraining14 Dec 2022
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activities30 Sep 2022
- 2022Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communications30 Mar 2022
- 2022Safe AI -- How is this Possible?25 Jan 2022
- 2022A causal model of safety assurance for machine learning14 Jan 2022
- 2022Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings3 Jan 2022
- 2021Network Generalization Prediction for Safety Critical Tasks in Novel Operating Domains17 Aug 2021
12 newest of 13 All 13 (JSON)