A High Dimensional Model for Adversarial Training: Geometry and Trade-Offs
K Tanner, M Vilucchio, B Loureiro… - arXiv preprint arXiv …, 2024 - arxiv.org
This work investigates adversarial training in the context of margin-based linear classifiers in
the high-dimensional regime where the dimension $ d $ and the number of data points $ n …
the high-dimensional regime where the dimension $ d $ and the number of data points $ n …
Direct Adversarial Latent Estimation to Evaluate Decision Boundary Complexity in Black Box Models
AS Dale, L Christopher - IEEE Transactions on Artificial …, 2024 - ieeexplore.ieee.org
A trustworthy AI model should be robust to perturbed data, where robustness correlates with
the dimensionality and linearity of feature representations in the model latent space. Existing …
the dimensionality and linearity of feature representations in the model latent space. Existing …
Eigenpatches—Adversarial Patches from Principal Components
Adversarial patches are still a simple yet powerful white-box attack that can be used to fool
object detectors by suppressing possible detections. The patches of these so-called evasion …
object detectors by suppressing possible detections. The patches of these so-called evasion …