Related papers: Evaluating Single Event Upsets in Deep Neural Netw…
Deep Neural Networks (DNNs) achieve strong performance in semantic segmentation for robotic perception but remain vulnerable to adversarial attacks, threatening safety-critical applications. While robustness has been studied for image…
Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, or natural language processing. Recently they also have been applied to various software engineering tasks,…
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…
Defect detection is a basic and essential task in automatic parts production, especially for automotive engine precision parts. In this paper, we propose a new idea to construct a deep convolutional network combining related knowledge of…
State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…
Despite their success, deep networks have been shown to be highly susceptible to perturbations, often causing significant drops in accuracy. In this paper, we investigate model robustness on perturbed inputs by studying the performance of…
Designing integrated circuits in radiation environments such as the High Luminosity LHC (HL-LHC) is challenging. Integrated circuits will be exposed to radiation-induced Single Event Effects (SEE). In deep sub-micron technology devices, the…
This paper studies the dependability of the Xilinx Deep-Learning Processing Unit (DPU) under neutron irradiation. It analyses the impact of Single Event Effects (SEEs) on the accuracy of the DPU running the resnet50 model on a Xilinx…
In order to deploy deep neural networks (DNNs) in high-stakes scenarios, it is imperative that DNNs provide inference robust to external perturbations - both intentional and unintentional. Although the resilience of DNNs to intentional and…
Event-based sensors offer significant advantages over traditional frame-based cameras, especially in scenarios involving rapid motion or challenging lighting conditions. However, event data frequently suffers from considerable noise,…
Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This paper studies the robustness of SNNs against adversarial…
Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but…
Deep Neural Networks (DNNs) are increasingly deployed in safety-critical applications including autonomous vehicles and medical diagnostics. To reduce the residual risk for unexpected DNN behaviour and provide evidence for their trustworthy…
Deep neural networks (DNNs) have been widely applied to solve real-world regression problems. However, selecting optimal network structures remains a significant challenge. This study addresses this issue by linking neuron selection in DNNs…
Deep Neural Networks have proven to be highly accurate at a variety of tasks in recent years. The benefits of Deep Neural Networks have also been embraced in power grids to detect False Data Injection Attacks (FDIA) while conducting…
An important challenge for human-like AI is compositional semantics. Recent research has attempted to address this by using deep neural networks to learn vector space embeddings of sentences, which then serve as input to other tasks. We…
Despite the widespread utilization of deep neural networks (DNNs) for speech emotion recognition (SER), they are severely restricted due to the paucity of labeled data for training. Recently, segment-based approaches for SER have been…
Deep Neural Networks (DNNs) are widely being adopted for safety-critical applications, e.g., healthcare and autonomous driving. Inherently, they are considered to be highly error-tolerant. However, recent studies have shown that hardware…
Software engineering techniques are increasingly relying on deep learning approaches to support many software engineering tasks, from bug triaging to code generation. To assess the efficacy of such techniques researchers typically perform…
Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN…