Published Jun 22, 2018
Defending Against Adversarial Attacks
Gokula Krishnan from ETH Zurich shares groundbreaking strategies for defending against adversarial attacks using Generative Adversarial Networks (GANs), highlighting his Cowboy algorithm and the innovative role of neural network regularization techniques to strengthen machine learning model robustness.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Adversarial Explanations
Answers 383 questions
Multi-Agent Diverse Generative Adversarial Networks
Answers 383 questions
Robustness to Unforeseen Adversarial Attacks
Answers 383 questions
Machine Learning Done Wrong
Answers 383 questions
Fooling Computer Vision
Answers 383 questions[MINI] Generative Adversarial Networks
Answers 383 questions
Visualization and Interpretability
Answers 383 questions
Easily Fooling Deep Neural Networks
Answers 383 questions
The Computational Complexity of Machine Learning
Answers 383 questions
Understanding Neural Networks
Answers 383 questions
Visual Illusions Deceiving Neural Networks
Answers 383 questions
Algorithmic Detection of Fake News
Answers 383 questions
ML Ops
Answers 383 questions
Fraud Detection with Graphs
Answers 383 questions
Detecting Ransomware
Answers 383 questions