Explore efficient defense strategies against adversarial examples in deep neural networks in this 28-minute conference talk from DefCamp 2017. Delve into the latest research and practices in the field of information security, focusing on protecting machine learning models from malicious attacks. Learn about the vulnerabilities of deep neural networks and discover practical techniques to enhance their robustness against adversarial inputs. Gain valuable insights from security specialists and researchers as they discuss cutting-edge approaches to safeguarding AI systems in an increasingly complex threat landscape.
Efficient Defenses Against Adversarial Examples for Deep Neural Networks
Overview
Syllabus
DefCamp 2017 - Efficient Defenses Against Adversarial Examples for Deep Neural Networks
Taught by
DefCamp
Related Courses
-
Keras Deep Learning & Generative Adversarial Networks (GAN)
-
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
-
Getting Robust - Securing Neural Networks Against Adversarial Attacks
-
Adversarial Examples in Deep Learning
-
Certified Robustness to Adversarial Examples with Differential Privacy
-
Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples
