Split Computing has emerged as a promising paradigm for deploying Deep Neural Networks in Edge and Inter-net of Things systems, enabling inference tasks to be distributed between resource-constrained edge devices and cloud servers. This approach is particularly attractive for autonomous systems, where security and reliability may be critical. However, interme-diate feature maps transmitted between devices are vulnerable to corruption, which may result from intentional adversarial attacks or unintentional hardware faults. Distinguishing whether corruption originates from an external adversary or an inherent system fault is crucial for implementing appropriate counter-measures-reinforcing security mechanisms against attacks or improving system reliability to mitigate the effects of hardware-related faults. To the best of our knowledge, this work is the first to propose a machine learning-based classification mechanism capable of differentiating adversarial attacks from hardware defects in Split Computing systems. The proposed approach analyzes the intermediate feature maps transmitted from the edge device to the server, classifying the source of corruption to guide appropriate responses. Experimental results demonstrate that one of the proposed classifiers can distinguish between intentional and unintentional feature map corruptions with an accuracy of 93.91 %.

Abstract The increasing complexity of Safety-Critical Real-Time Embedded Systems (SACRES) presents significant challenges regarding reliability, security, and trustworthiness. Key concerns include the system’s vulnerability to instantaneous voltage spikes, electromagnetic interference, neutron strikes, and temperatures out of range, which can induce bit-flipping and consequentially temporary corruption of stored memory data and soft errors. These errors may result in system faults that could push the system into dangerous states. In high-stakes fields like automotive, aerospace, and avionics, such failures can have serious, real-world consequences, potentially endangering lives. This paper introduces an innovative, fully configurable fault injection tool designed to monitor and analyze the micro-architectural state of the system. This tool allows a tailored injection campaign, including both CPU registers and RAM, with a flexible fault model able to inject single and multi-bit-flipping in the application and Operating System (OS) space. Tracking the architectural events using the microprocessor’s Performance Monitoring Unit (PMU) and debugging interface. A key feature is its ability to ensure the repeatability of fault injections, which focus on bit-flipping in memory systems. The results of these fault injections allow for a detailed analysis of how soft errors affect system performance, output integrity, and timing predictability, all of which are critical in SACRES.

This paper aims to comprehensively explore challenges and opportunities to design highly efficient Neural Network (NN) systems through Approximate Computing (AxC) techniques while ensuring fault tolerance properties. By highlighting the intrinsic conflicting goals of AxC and fault tolerance principles, the study aims to stimulate and contribute to a deeper understanding of how important it is to consider fault tolerance requirements while designing approximate-computing-based systems. This is key to developing highly efficient fault-tolerant architectures for Neural Networks.

As artificial neural networks have become increasingly integrated into safety-critical systems such as autonomous vehicles, devices for medical diagnosis, and industrial automation, ensuring their reliability in the face of random hardware faults becomes paramount. This paper introduces SpikingJET, a novel fault injector designed specifically for fully connected and convolutional Spiking Neural Networks (SNNs). Our work underscores the critical need to evaluate the resilience of SNNs to hardware faults, considering their growing prominence in real-world applications. SpikingJET provides a comprehensive platform for assessing the resilience of SNNs by inducing errors and injecting faults into critical components such as synaptic weights, neuron model parameters, internal states, and activation functions. This paper demonstrates the effectiveness of SpikingJET through extensive software-level experiments on various SNN architectures, revealing insights into their vulnerability and resilience to hardware faults. Moreover, highlighting the importance of fault resilience in SNNs contributes to the ongoing effort to enhance the reliability and safety of Neural Network (NN)-powered systems in diverse domains.