Targeted Adversarial Examples for Black Box Audio
Generating targeted adversarial perturbation examples against black-box automated speech recognition systems.
Summary
DEF CON Security Research Presentation
This talk covers technical security topics and vulnerability research presented at DEF CON. The presentation includes discussion of contemporary security challenges, demonstrations of exploitation techniques, and insights into defensive countermeasures and best practices.
(AI summary — Claude Haiku)
Related talks
AI Village·33 min
Moustafa Alzantot · Yash Sharma
Practical black-box and gradient-free adversarial attack methodologies against machine learning systems.
AI Village·10 min
Hou · Zhou
Creating transferable adversarial perturbations that reliably fool multiple disparate machine learning architectures.
AI Village·19 min
Guo · Cuevas
An overview of recent progress and developments in adversarial deep learning attacks and defenses.