Related papers: MRFI: An Open Source Multi-Resolution Fault Inject…
Electromagnetic Fault Injection (EMFI) is a powerful technique for inducing bit flips and instruction-level perturbations on microcontrollers, yet existing literature lacks a unified methodology for systematically mapping spatial…
Deep Neural Networks (DNNs) and their accelerators are being deployed ever more frequently in safety-critical applications leading to increasing reliability concerns. A traditional and accurate method for assessing DNNs' reliability has…
This paper describes NCRF++, a toolkit for neural sequence labeling. NCRF++ is designed for quick implementation of different neural sequence labeling models with a CRF inference layer. It provides users with an inference for building the…
Designing and implementing efficient, provably correct parallel neural network processing is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and Pthreads…
Mobile cellular network operators spend nearly a quarter of their revenue on network maintenance and management. A significant portion of that budget is spent on resolving faults diagnosed in the system that disrupt or degrade cellular…
Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have…
We propose ReMiDi, a novel method for inferring neuronal microstructure as arbitrary 3D meshes using a differentiable diffusion Magnetic Resonance Imaging (dMRI) simulator. We first implemented in PyTorch a differentiable dMRI simulator…
Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning…
The Functional Failure Rate analysis of today's complex circuits is a difficult task and requires a significant investment in terms of human efforts, processing resources and tool licenses. Thereby, de-rating or vulnerability factors are a…
Input-sensitive profiling is a recent performance analysis technique that makes it possible to estimate the empirical cost function of individual routines of a program, helping developers understand how performance scales to larger inputs…
For a deep learning model, efficient execution of its computation graph is key to achieving high performance. Previous work has focused on improving the performance for individual nodes of the computation graph, while ignoring the…
Radio frequency fingerprint identification (RFFI) can classify wireless devices by analyzing the signal distortions caused by the intrinsic hardware impairments. State-of-the-art neural networks have been adopted for RFFI. However, many…
FPGAs are now ubiquitous in cloud computing infrastructures and reconfigurable system-on-chip, particularly for AI acceleration. Major cloud service providers such as Amazon and Microsoft are increasingly incorporating FPGAs for specialized…
Deep Learning Accelerators are prone to faults which manifest in the form of errors in Neural Networks. Fault Tolerance in Neural Networks is crucial in real-time safety critical applications requiring computation for long durations. Neural…
Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional trained classifier to detect and correct the adversarial samples,…
As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these…
The development of smart systems (i.e., systems enhanced with AI components) has thrived thanks to the rapid advancements in neural networks (NNs). A wide range of libraries and frameworks have consequently emerged to support NN design and…
With the rapid advancements of deep learning in the past decade, it can be foreseen that deep learning will be continuously deployed in more and more safety-critical applications such as autonomous driving and robotics. In this context,…
Program errors can occur in any type of programming, and can manifest in a variety of ways, such as unexpected output, crashes, or performance issues. And program error diagnosis can often be too abstract or technical for developers to…
Creating resilient machine learning (ML) systems has become necessary to ensure production-ready ML systems that acquire user confidence seamlessly. The quality of the input data and the model highly influence the successful end-to-end…