声纹识别领域对抗攻击和防御论文整理

1.   FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances.(paper)

2.   Attack on Practical Speaker Verification Systerm Using Universal Adversarial Perturbations.(Paper)

3.   Learning to fool the speaker recognition. [Jiguo Li, ..] (paper、code、Web)

1.   Adversarial Defense for Deep Speaker Recognition Using Hybrid Dversarial Training. [Monisankha Pal, Arindam Jati..] (paper)

2.   Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models. [Haibin Wu;Xu Li..] (paper)

3.   Voting for the right answer: Adversarial defense for speaker verification.(paper)

ps:some logo:https://www.webfx.com/tools/emoji-cheat-sheet/