TARL replaces Triangle Attack's fixed angle-update rule with a Q-learning policy, reporting comparable attack success on ImageNet and CIFAR-10 with 500 queries instead of 1,000.
Obfu scated gradients give a false sense of security: Circumventing defenses to advers arial examples
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack
TARL replaces Triangle Attack's fixed angle-update rule with a Q-learning policy, reporting comparable attack success on ImageNet and CIFAR-10 with 500 queries instead of 1,000.