Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
Martin Anthony, Kaveh Salehzadeh Nobari
stat.ML, cs.LG
Submitted: 2026-06-17
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- FinBERT: Financial Sentiment Analysis with Pre-trained Language Models
- Explaining and Harnessing Adversarial Examples
- Categorical Reparameterization with Gumbel-Softmax
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Intriguing properties of neural networks
- Ensemble Adversarial Training: Attacks and Defenses
- Robustness May Be at Odds with Accuracy
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier