▌system-one

~ / evaluation / class-native-suites / jevadvbench

JevAdvBench

The first adversarial benchmark for the class: black-box attacks flip 46.3% of Jev's correct decisions, and the transfer attacks generalize across tasks. The evaluation companion to the injection papers under Reading.

section
Evaluation
group
Class-native suites
source
arxiv.org
added to list
nov 12

also in Class-native suites