From b1acb76b2fb5fd76e1bd823e599f96ec3992cfb3 Mon Sep 17 00:00:00 2001 From: Alexey Kurakin Date: Thu, 24 Aug 2017 10:56:20 -0700 Subject: [PATCH] Another small update to README.md --- examples/nips17_adversarial_competition/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/nips17_adversarial_competition/README.md b/examples/nips17_adversarial_competition/README.md index 3136cbf1d..1216fa42b 100644 --- a/examples/nips17_adversarial_competition/README.md +++ b/examples/nips17_adversarial_competition/README.md @@ -69,7 +69,7 @@ Toolkit includes examples of attacks and defenses in the following directories: class attack. This is not particularly good targeted attack, but it demonstrates how targeted attack could be written. * `sample_targeted_attacks/iter_target_class/` - iterative target class - attack. This is pretty good white-box attack, + attack. This is a pretty good white-box attack, but it does not do well in black box setting. * `sample_defenses/` - directory with examples of defenses: * `sample_defenses/base_inception_model/` - baseline inception classifier,