works on
intermediate features 1reference selection 1representation analysis 1semantic alignment 1synthetic image attribution 1training-free methods 1

From the 1 of 10 linked papers with an AI index.

activity
20242026
collaborators
Showing stat.MLShow all

1 paper · 1 filter

stat.ML2026

The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples

Nasrin Malekzadeh Goradel, Niccolo Pancino, Yaser Gholizade Atani +3

Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions unde…