[HTML][HTML] Ai system engineering—key challenges and lessons learned
The main challenges are discussed together with the lessons learned from past and
ongoing research along the development cycle of machine learning systems. This will be …
ongoing research along the development cycle of machine learning systems. This will be …
[HTML][HTML] Modeling threats to AI-ML systems using STRIDE
The application of emerging technologies, such as Artificial Intelligence (AI), entails risks that
need to be addressed to ensure secure and trustworthy socio-technical infrastructures …
need to be addressed to ensure secure and trustworthy socio-technical infrastructures …
[HTML][HTML] Diffeomorphic transforms for data augmentation of highly variable shape and texture objects
Background and objective: Training a deep convolutional neural network (CNN) for
automatic image classification requires a large database with images of labeled samples …
automatic image classification requires a large database with images of labeled samples …
Stride-ai: An approach to identifying vulnerabilities of machine learning assets
We propose a security methodology for Machine Learning (ML) pipelines, supporting the
definition of key security properties of ML assets, the identification of threats to them as well …
definition of key security properties of ML assets, the identification of threats to them as well …
ContRE: A Complementary Measure for Robustness Evaluation of Deep Networks via Contrastive Examples
Training images with data transformations, eg, crops, shifts, rotations and color distortions,
have been suggested as contrastive examples to evaluate the robustness of deep neural …
have been suggested as contrastive examples to evaluate the robustness of deep neural …
DAD++: Improved Data-free Test Time Adversarial Defense
With the increasing deployment of deep neural networks in safety-critical applications such
as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has …
as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has …
Practical assessment of generalization performance robustness for deep networks via contrastive examples
Training images with data transformations have been suggested as contrastive examples to
complement the testing set for generalization performance evaluation of deep neural …
complement the testing set for generalization performance evaluation of deep neural …
[HTML][HTML] Structural causal models reveal confounder bias in linear program modelling
The recent years have been marked by extended research on adversarial attacks, especially
on deep neural networks. With this work we intend on posing and investigating the question …
on deep neural networks. With this work we intend on posing and investigating the question …
[PDF][PDF] How Much is an Augmented Sample Worth?
H Eghbal-zadeh, G Widmer - preregister.science
Data Augmentation (DA) methods are widely-used in various areas of machine learning,
and have been associated with the generalization capabilities of deep neural networks …
and have been associated with the generalization capabilities of deep neural networks …
Transferable Unsupervised Robust Representation Learning
Robustness is an important, and yet, under-explored aspect of unsupervised representation
learning, which has seen a lot of recent developments. In this work, we address this gap by …
learning, which has seen a lot of recent developments. In this work, we address this gap by …