Detecting Audio Adversarial Examples with Logit Noising
Namgyu Park, Sangwoo Ji, Jong Kyoung Kim · Annual Computer Security Applications Conference · 2021
Automatic speech recognition (ASR) systems are vulnerable to audio adversarial examples that attempt to deceive ASR systems by adding perturbations to benign speech signals. Although an adversarial example and the original benign wave are indistinguishable to humans, the former is transcribed as a malicious target sentence by ASR systems. Several methods have been proposed to generate audio adversarial examples and feed them directly into the ASR system (over-line). Furthermore, many researchers have demonstrated the feasibility of robust physical audio adversarial examples (over-air). To defend against the attacks, several studies have been proposed. However, deploying them in a real-world situation is difficult because of accuracy drop or time overhead.