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.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example

Benedetta Tondi, Wei Guo, Niccolò Pancino +1

Most of the approaches proposed so far to craft targeted adversarial examples against Deep Learning classifiers are highly suboptimal and typically rely on increasing the likelihoo…