Generalizing Adversarial Features
Tim and Florian discuss the transfer of adversarial examples between models, highlighting the presence of generalizing features imperceptible to humans. They explore the concept of discriminating allowed features and the role of adversarial training in enhancing model robustness to perturbations.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)
Related Questions
How can we defend against adversarial attacks on machine learning models as discussed in the episode #52 - Unadversarial Examples (Hadi Salman, MIT) and the clip Neural Network Features?
What are adversarial attacks on machine learning models as discussed in the episode #52 - Unadversarial Examples (Hadi Salman, MIT) and the clip Neural Network Features?
What are adversarial attacks on machine learning models as discussed in the episode #52 - Unadversarial Examples (Hadi Salman, MIT) and the clip Neural Network Features?