285 citations · 285 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
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…
cs.LG2020★ 285 cited
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh, Shiori Sagawa, Henrik Marklund +20
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the…