Annachiara Ruospo

The reliability assessment of systems powered by artificial intelligence (AI) is becoming a crucial step prior to their deployment in safety and mission-critical systems. Recently, many efforts have been made to develop sophisticated techniques to evaluate and improve the resilience of AI models against the occurrence of random hardware faults. However, due to the intrinsic nature of such models, the comparison of the results obtained in state-of-the-art works is crucial, as reference models are missing. Moreover, their resilience is strongly influenced by the training process, the adopted framework and data representation, and so on. To enable a common ground for future research targeting CNN resilience analysis/hardening, this work proposes a first benchmark suite of DL models commonly adopted in this context, providing the models, the training/test data, and the resilience-related information (fault list, coverage, etc.) that can be used as a baseline for fair comparison. To this end, this research identifies a set of axes that have an impact on the resilience and classifies some popular CNN models, in both PyTorch and TensorFlow. Some final considerations are drawn, showing the relevance of a benchmark suite tailored for the resilience context.

The complexity of the state-of-the-art devices makes reliability assessments approaches extremely complex and, sometimes, out of the timing constraints and computational capabilities. Fault Injections (FIs) are one of the most used approaches for evaluating the dependability of safety-critical systems. With billion-transistor hardware devices running trillion-parameter deep neural networks, injecting the entire fault universe is unfeasible. A widespread solution consists in performing statistical fault injections (SFIs), injecting a subset of faults to estimate a characteristic with an error margin and a confidence level. This research work presents an iterative SFI approach to estimate failure rates in convolutional neural networks (CNNs), i.e., the percentage of wrong predictions caused by random hardware faults affecting synaptic weights. SFIs at different granularities have been performed with margin of errors equal to 1%, 0.1%, and 0.01%. Results for two CNNs (ResNet20 and MobileNetV2) are presented and experimentally and statistically demonstrate the effectiveness of the proposed approach. For instance, to estimate the network-wise failure rate with an error margin of 0.01%, the proposed approach reduces the total injected faults by about 66% and 90% compared to conservative methods, and by 1.94% and 1.65% compared to iterative SFI methods in the literature, for ResNet20 and MobileNetV2, respectively.

Nowadays, Deep Neural Networks (DNNs) are widely used in safety-critical fields such as automotive and healthcare, where their reliability is crucial due to their direct impact on human lives. Over the years, evaluating their resilience through software-level fault injection experiments has become a common research approach. The corruption of individual bits in the model’s parameters has been one of the most studied fault models in the last decade. This work introduces a methodology to evaluate the impact of permanent faults on DNN weights in image classification and object detection tasks, highlighting key ideas, main contributions, and the research’s impact over time.

With the advent of tinyML, IoT devices have expanded their range of operations from simple data gathering and transmission to full-fledged inference. This expansion has been further enabled by the rise in popularity of open-source hardware, with the RISC-V architecture being the most prominent example. TinyML's decentralization can solve the current privacy and security issues of IoT infrastructures. However, it also shifts the burden of security on already resource-constrained devices. Ultra-low-power devices, in particular, often sacrifice security features for energy and area efficiency. This work aims at showing that, in the context of edge computing based on open-source hardware, neglecting hardware security features for the sake of efficiency is not an acceptable trade-off with respect to AI security.

Deep learning (DL) reliability is becoming a growing concern, and efficient reliability assessment approaches are required to meet safety constraints. This article presents a survey of the main DL reliability assessment methodologies, focusing mainly on fault injection techniques used to evaluate DL resilience.