Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to …
L Rice, E Wong, Z Kolter - International conference on …, 2020 - proceedings.mlr.press
It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically …
A Huertas Celdran, J Kreischer, M Demirci… - CEUR Workshop …, 2023 - zora.uzh.ch
Trusting Artificial Intelligence (AI) is controversial since models and predictions might not be fair, understandable by humans, robust against adversaries, or trained appropriately …
We study the problem of training certifiably robust models against adversarial examples. Certifiable training minimizes an upper bound on the worst-case loss over the allowed …
Machine learning (ML) has advanced dramatically during the past decade and continues to achieve impressive human-level performance on nontrivial tasks in image, speech, and text …
Phenomenon-specific" adversarial" datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed …
Batch Normalization (BatchNorm) is effective for improving the performance and accelerating the training of deep neural networks. However, it has also shown to be a cause …