24 citations · 96 across the 43 of their papers we have counts for
14 papers · 1 filter
Safety Performance of Neural Networks in the Presence of Covariate Shift
Chih-Hong Cheng, Harald Ruess, Konstantinos Theodorou
Covariate shift may impact the operational safety performance of neural networks. A re-evaluation of the safety performance, however, requires collecting new operational data and c…
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Saddek Bensalem, Chih-Hong Cheng, Wei Huang +3
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it…
Towards Rigorous Design of OoD Detectors
Chih-Hong Cheng, Changshun Wu, Harald Ruess +1
Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. We are arguing, however, that current performance-oriented OoD detection techniq…
Potential-based Credit Assignment for Cooperative RL-based Testing of Autonomous Vehicles
Utku Ayvaz, Chih-Hong Cheng, Hao Shen
While autonomous vehicles (AVs) may perform remarkably well in generic real-life cases, their irrational action in some unforeseen cases leads to critical safety concerns. This pap…
Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection
Tobias Schuster, Emmanouil Seferis, Simon Burton +1
In this paper, we consider the imperfection within machine learning-based 2D object detection and its impact on safety. We address a special sub-type of performance limitations: th…
Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
Brian Hsuan-Cheng Liao, Chih-Hong Cheng, Hasan Esen +1
As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving. In this paper, we study the robu…
Provably-Robust Runtime Monitoring of Neuron Activation Patterns
Chih-Hong Cheng
For deep neural networks (DNNs) to be used in safety-critical autonomous driving tasks, it is desirable to monitor in operation time if the input for the DNN is similar to the data…
Continuous Safety Verification of Neural Networks
Chih-Hong Cheng, Rongjie Yan
Deploying deep neural networks (DNNs) as core functions in autonomous driving creates unique verification and validation challenges. In particular, the continuous engineering parad…
Safety-Aware Hardening of 3D Object Detection Neural Network Systems
Chih-Hong Cheng
We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the…
Towards Robust Direct Perception Networks for Automated Driving
Chih-Hong Cheng
We consider the problem of engineering robust direct perception neural networks with output being regression. Such networks take high dimensional input image data, and they produce…
nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems
Chih-Hong Cheng, Chung-Hao Huang, Georg Nührenberg
Can engineering neural networks be approached in a disciplined way similar to how engineers build software for civil aircraft? We present nn-dependability-kit, an open-source toolb…
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…
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…
Maximum Resilience of Artificial Neural Networks
Chih-Hong Cheng, Georg Nührenberg, Harald Ruess
The deployment of Artificial Neural Networks (ANNs) in safety-critical applications poses a number of new verification and certification challenges. In particular, for ANN-enabled…