19 citations · 39 across the 10 of their papers we have counts for
10 papers
Large-Scale Application of Fault Injection into PyTorch Models -- an Extension to PyTorchFI for Validation Efficiency
Ralf Graafe, Qutub Syed Sha, Florian Geissler +1
Transient or permanent faults in hardware can render the output of Neural Networks (NN) incorrect without user-specific traces of the error, i.e. silent data errors (SDE). On the o…
BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture
Syed Sha Qutub, Neslihan Kose, Rafael Rosales +6
This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial i…
Envisioning a Safety Island to Enable HPC Devices in Safety-Critical Domains
Jaume Abella, Francisco J. Cazorla, Sergi Alcaide +3
HPC (High Performance Computing) devices increasingly become the only alternative to deliver the performance needed in safety-critical autonomous systems (e.g., autonomous cars, un…
Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity
Rafael Rosales, Pablo Munoz, Michael Paulitsch
In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We…
Evaluation of Confidence-based Ensembling in Deep Learning Image Classification
Rafael Rosales, Peter Popov, Michael Paulitsch
Ensembling is a successful technique to improve the performance of machine learning (ML) models. Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confi…
Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization
Neslihan Kose, Ranganath Krishnan, Akash Dhamasia +2
Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making.…
Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs
Syed Qutub, Florian Geissler, Yang Peng +4
Object detection neural network models need to perform reliably in highly dynamic and safety-critical environments like automated driving or robotics. Therefore, it is paramount to…
Fault-Tolerant Perception for Automated Driving A Lightweight Monitoring Approach
Cornelius Buerkle, Florian Geissler, Michael Paulitsch +1
While the most visible part of the safety verification process of automated vehicles concerns the planning and control system, it is often overlooked that safety of the latter cruc…
Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision
Florian Geissler, Syed Qutub, Sayanta Roychowdhury +6
Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driv…
A Plausibility-based Fault Detection Method for High-level Fusion Perception Systems
Florian Geissler, Alex Unnervik, Michael Paulitsch
Trustworthy environment perception is the fundamental basis for the safe deployment of automated agents such as self-driving vehicles or intelligent robots. The problem remains tha…