Explore a practical Trojan attack against automatic speech recognition systems in this 15-minute IEEE conference talk. Learn about the TrojanModel approach presented by researchers from the University of Wollongong and Deakin University in Australia. Gain insights into potential vulnerabilities in speech recognition technology and understand the implications for cybersecurity in voice-activated systems.
TrojanModel - A Practical Trojan Attack against Automatic Speech Recognition Systems
Overview
Syllabus
TrojanModel: A Practical Trojan Attack against Automatic Speech Recognition Systems
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Hear "No Evil", See "Kenansville" - Efficient and Transferable Black-Box Attacks on Automatic Speech Recognition Systems
-
Practical Adversarial Attack Against Speech Recognition Platforms
-
SoK - The Faults in Our ASRs - An Overview of Attacks Against Automatic Speech Recognition and Speaker Identification Systems
-
ImU - Physical Impersonating Attack for Face Recognition System with Natural Style Changes
-
Trojan Source and Bad Characters - Invisible Hacks and Reluctant Patching
-
Audio Adversarial Examples - Targeted Attacks on Speech-to-Text
