C Urban, A Miné - arXiv preprint arXiv:2104.02466, 2021 - arxiv.org
We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems. Formal methods can provide rigorous correctness guarantees on …
Formal approaches can provide strict correctness guarantees for the development of both hardware and software systems. In this work, we examine state-of-the-art formal methods for …
L Li, T Xie, B Li - 2023 IEEE symposium on security and privacy …, 2023 - ieeexplore.ieee.org
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …
Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness …
S Biswas, H Rajan - 2023 IEEE/ACM 45th International …, 2023 - ieeexplore.ieee.org
Fairness of machine learning (ML) software has become a major concern in the recent past. Although recent research on testing and improving fairness have demonstrated impact on …
Convolutional neural networks (CNNs) have achieved immense popularity in areas like computer vision, image processing, speech proccessing, and many others. Unfortunately …
G Amir, O Maayan, T Zelazny, G Katz… - … Conference on Computer …, 2023 - Springer
Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the state of the art in numerous application domains. However, DNN-based decision rules are …
Fair representation learning is an attractive approach that promises fairness of downstream predictors by encoding sensitive data. Unfortunately, recent work has shown that strong …
X Yang, T Yamaguchi, HD Tran, B Hoxha… - … Conference on Formal …, 2022 - Springer
Safety is a critical concern for the next generation of autonomy that is likely to rely heavily on deep neural networks for perception and control. This paper proposes a method to repair …