Augmax: Adversarial composition of random augmentations for robust training
Data augmentation is a simple yet effective way to improve the robustness of deep neural
networks (DNNs). Diversity and hardness are two complementary dimensions of data …
networks (DNNs). Diversity and hardness are two complementary dimensions of data …
Causaladv: Adversarial robustness through the lens of causality
The adversarial vulnerability of deep neural networks has attracted significant attention in
machine learning. As causal reasoning has an instinct for modelling distribution change, it is …
machine learning. As causal reasoning has an instinct for modelling distribution change, it is …
Better safe than sorry: Preventing delusive adversaries with adversarial training
Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by
slightly perturbing the features of correctly labeled training examples. By formalizing this …
slightly perturbing the features of correctly labeled training examples. By formalizing this …
A deep learning approach for robust detection of bots in twitter using transformers
D Martín-Gutiérrez, G Hernández-Peñaloza… - IEEE …, 2021 - ieeexplore.ieee.org
During the last decades, the volume of multimedia content posted in social networks has
grown exponentially and such information is immediately propagated and consumed by a …
grown exponentially and such information is immediately propagated and consumed by a …
Probabilistic margins for instance reweighting in adversarial training
Reweighting adversarial data during training has been recently shown to improve
adversarial robustness, where data closer to the current decision boundaries are regarded …
adversarial robustness, where data closer to the current decision boundaries are regarded …
Image-based scam detection method using an attention capsule network
L Bian, L Zhang, K Zhao, H Wang, S Gong - IEEE Access, 2021 - ieeexplore.ieee.org
In recent years, the rapid development of blockchain technology has attracted much
attention from people around the world. Scammers take advantage of the pseudo-anonymity …
attention from people around the world. Scammers take advantage of the pseudo-anonymity …
Sparse and imperceptible adversarial attack via a homotopy algorithm
Sparse adversarial attacks can fool deep neural networks (DNNs) by only perturbing a few
pixels (regularized by $\ell_0 $ norm). Recent efforts combine it with another $\ell_\infty …
pixels (regularized by $\ell_0 $ norm). Recent efforts combine it with another $\ell_\infty …
Learning to generate visual questions with noisy supervision
The task of visual question generation (VQG) aims to generate human-like neural questions
from an image and potentially other side information (eg, answer type or the answer itself) …
from an image and potentially other side information (eg, answer type or the answer itself) …
Meta two-sample testing: Learning kernels for testing with limited data
Modern kernel-based two-sample tests have shown great success in distinguishing
complex, high-dimensional distributions by learning appropriate kernels (or, as a special …
complex, high-dimensional distributions by learning appropriate kernels (or, as a special …
Efficient statistical tests: A neural tangent kernel approach
For machine learning models to make reliable predictions in deployment, one needs to
ensure the previously unknown test samples need to be sufficiently similar to the training …
ensure the previously unknown test samples need to be sufficiently similar to the training …