Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision
This addresses safety concerns for CNNs in critical domains like automated driving, but it is incremental as it builds on existing activation clipping techniques.
The paper tackled the problem of ensuring robustness in convolutional neural networks (CNNs) against hardware soft errors in safety-critical applications, demonstrating that activation range supervision is a highly reliable fault detector and mitigator with up to eight-exponent floating point representation, with benefits shown in a vehicle classification scenario using ResNet-50 and the MIOVision dataset.
Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driving. Real-world implementations will need to guarantee their robustness against hardware soft errors corrupting the underlying platform memory. Based on the previously observed efficacy of activation clipping techniques, we build a prototypical safety case for classifier CNNs by demonstrating that range supervision represents a highly reliable fault detector and mitigator with respect to relevant bit flips, adopting an eight-exponent floating point data representation. We further explore novel, non-uniform range restriction methods that effectively suppress the probability of silent data corruptions and uncorrectable errors. As a safety-relevant end-to-end use case, we showcase the benefit of our approach in a vehicle classification scenario, using ResNet-50 and the traffic camera data set MIOVision. The quantitative evidence provided in this work can be leveraged to inspire further and possibly more complex CNN safety arguments.