Related papers: MRFI: An Open Source Multi-Resolution Fault Inject…

This paper presents a software-based technique to recover control-flow errors in multithreaded programs. Control-flow error recovery is achieved through inserting additional instructions into multithreaded program at compile time regarding…

Deep Learning (DL) algorithms have become the de facto Machine Learning (ML) algorithm for large scale data analysis. DL algorithms are computationally expensive - even distributed DL implementations which use MPI require days of training…

Electromagnetic fault injection (EMFI) is a well known technique used to disturb the behaviour of a chip for weakening its security. These attacks are mostly done on simple microcontrollers. On these targets, the fault effects are…

Fine-tuning is now the primary method for adapting large neural networks, but it also introduces new integrity risks. An untrusted party can insert backdoors, change safety behavior, or overwrite large parts of a model while claiming only…

We present FINJ, a high-level fault injection tool for High-Performance Computing (HPC) systems, with a focus on the management of complex experiments. FINJ provides support for custom workloads and allows generation of anomalous conditions…

Upcoming certification actions related to the security of machine learning (ML) based systems raise major evaluation challenges that are amplified by the large-scale deployment of models in many hardware platforms. Until recently, most of…

As large language models (LLMs) become more capable, there is an urgent need for interpretable and transparent tools. Current methods are difficult to implement, and accessible tools to analyze model internals are lacking. To bridge this…

Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a change of value that is currently being computed. They can be…

The emergence of latency-critical AI applications has been supported by the evolution of the edge computing paradigm. However, edge solutions are typically resource-constrained, posing reliability challenges due to heightened contention for…

Satellites are used for a multitude of applications, including communications, Earth observation, and space science. Neural networks and deep learning-based approaches now represent the state-of-the-art to enhance the performance and…

Deep neural networks have shown exemplary performance on semantic scene understanding tasks on source domains, but due to the absence of style diversity during training, enhancing performance on unseen target domains using only single…

Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge overheads, specifically when used for fine-tuning large DNNs…

Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Traditional software fault injection methods, while foundational, face limitations in adequately representing real-world faults, offering customization, and requiring significant manual effort and expertise. This paper introduces a novel…

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

This paper proposes OpenPARF, an open-source placement and routing framework for large-scale FPGA designs. OpenPARF is implemented with the deep learning toolkit PyTorch and supports massive parallelization on GPU. The framework proposes a…

Convolutional Neural Networks have rapidly become the most successful machine learning algorithm, enabling ubiquitous machine vision and intelligent decisions on even embedded computing-systems. While the underlying arithmetic is…

Neural networks are often susceptible to minor perturbations in input that cause them to misclassify. A recent solution to this problem is the use of globally-robust neural networks, which employ a function to certify that the…

Simulations with high accuracy are an essential part of scientific research to accelerate the innovation process. They are especially useful for finding novel approaches or optimizing existing methods. Today, powerful software tools are…