I am a Ph.D. Candidate from the Department of Computer Science and Technology, Tsinghua University under the supervision of Prof. Xiaolin Hu. I am a member of the Tsinghua Statistical Artificial Intelligence & Learning (TSAIL) Group. My research interests include the application of artificial intelligence and machine learning in finance, insurance, speech, and audio processing. I am also currently the vice-president of the Data Science and AI Association of Australia (DSAI).
I have over 8 years of industrial experience in data science, actuarial, and managerial roles in multinational corporations across Australia and the surrounding regions.
Ph.D. in Artificial Intelligence
Tsinghua University
MEng in Computer Science
University of New South Wales
BSc in Mathematics and Statistics
University of New South Wales
In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text. Previous studies played an audio adversarial example as a digital signal to perform physical attacks, which would be easily rejected by audio replay detection modules. This work shows that by playing our crafted adversarial perturbation as a separate source when the adversary is speaking, the the practical speaker verification system will misjudge the adversary as a target speaker. A two-step algorithm is proposed to optimize the universal adversarial perturbation to be text-independent and has little effect on authentication text recognition. We also estimated room impulse response (RIR) in the algorithm which allowed the perturbation to be effective after being played over the air. In the physical experiment, we achieved targeted attacks with a success rate of 100%, while the word error rate (WER) on speech recognition only increased by 3.55%. And recorded audio could pass replay detection for the live person speaking.
Please feel free to contact me for any questions.