IEEE Symposium on Security and Privacy·22 min
Engineers explore architecture and security mechanisms for Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks.
neural-networksnetworksdistillation+3
2 talks tagged with this topic.
Loading filters…
1–2 of 2 talks · loading…
IEEE Symposium on Security and Privacy·22 min
Engineers explore architecture and security mechanisms for Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks.
IEEE Symposium on Security and Privacy·13 min
Generative Models
Presenters detail vulnerability discovery and exploitation in Learning Universal Adversarial Perturbations with Generative Models.