How to certify machine learning based safety-critical systems? A systematic literature review
Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …
past years. However, including it in so-called “safety-critical” systems such as automotive or …
Towards energy-efficient and secure edge AI: A cross-layer framework ICCAD special session paper
The security and privacy concerns along with the amount of data that is required to be
processed on regular basis has pushed processing to the edge of the computing systems …
processed on regular basis has pushed processing to the edge of the computing systems …
A novel gapg approach to automatic property generation for formal verification: The gan perspective
H Gao, B Dai, H Miao, X Yang, RJD Barroso… - ACM Transactions on …, 2023 - dl.acm.org
Formal methods have been widely used to support software testing to guarantee correctness
and reliability. For example, model checking technology attempts to ensure that the …
and reliability. For example, model checking technology attempts to ensure that the …
Multilayered review of safety approaches for machine learning-based systems in the days of AI
The unprecedented advancement of artificial intelligence (AI) in recent years has altered our
perspectives on software engineering and systems engineering as a whole. Nowadays …
perspectives on software engineering and systems engineering as a whole. Nowadays …
Special session: Towards an agile design methodology for efficient, reliable, and secure ML systems
The real-world use cases of Machine Learning (ML) have exploded over the past few years.
However, the current computing infrastructure is insufficient to support all real-world …
However, the current computing infrastructure is insufficient to support all real-world …
Coupling algebraic topology theory, formal methods and safety requirements toward a new coverage metric for artificial intelligence models
F Adjed, M Mziou-Sallami, F Pelliccia… - Neural Computing and …, 2022 - Springer
Safety requirements are among the main barriers to the industrialization of machine learning
based on deep learning architectures. In this work, a new metric of data coverage is …
based on deep learning architectures. In this work, a new metric of data coverage is …
UnbiasedNets: a dataset diversification framework for robustness bias alleviation in neural networks
Performance of trained neural network (NN) models, in terms of testing accuracy, has
improved remarkably over the past several years, especially with the advent of deep …
improved remarkably over the past several years, especially with the advent of deep …
Dependable deep learning: Towards cost-efficient resilience of deep neural network accelerators against soft errors and permanent faults
MA Hanif, M Shafique - … Symposium on On-Line Testing and …, 2020 - ieeexplore.ieee.org
Deep Learning has enabled machines to learn computational models (ie, Deep Neural
Networks-DNNs) that can perform certain complex tasks with claims to be close to human …
Networks-DNNs) that can perform certain complex tasks with claims to be close to human …
QuanDA: GPU accelerated quantitative deep neural network analysis
M Naseer, O Hasan, M Shafique - ACM Transactions on Design …, 2023 - dl.acm.org
Over the past years, numerous studies demonstrated the vulnerability of deep neural
networks (DNNs) to make correct classifications in the presence of small noise. This …
networks (DNNs) to make correct classifications in the presence of small noise. This …
A hybrid regularized multilayer perceptron for input noise immunity
The immunity of multilayer perceptron (MLP) is less effective toward input noise. In this
article, we have focused on the robustness of MLP with respect to input noise where noise …
article, we have focused on the robustness of MLP with respect to input noise where noise …