The Devil is in the GAN: Defending Deep Generative Models Against Adversarial Attacks
Security researchers examine technical aspects of The Devil is in the GAN: Defending Deep Generative Models Against Adversarial Attacks.
Summary
Defends deep generative models against adversarial attacks in GANs.
Related talks
Eye on Tech·40 min
Security researchers examine technical aspects of Box content management generative AI route is model-agnostic.
contentmanagementgenerative+3
Eye on Tech·3 min
Sabrina Polin
Engineers explore architecture and security mechanisms for What is a Foundation Model? (Generative AI).
foundationmodelgenerative
IEEE Symposium on Security and Privacy·23 min
Presenters detail vulnerability discovery and exploitation in Differentially Private Model Publishing For Deep Learning.
deep-learningdifferentiallyprivate+3