I’m an undergraduate student majoring in Cyberspace Security (Experimental Class) at Beijing University of Posts and Telecommunications (BUPT). My research interests lie in Trustworthy AI, Adversarial Machine Learning, and Speech Security. I have been working under the supervision of Prof. Jie Hao in the National Engineering Research Center of Disaster Backup and Recovery. I also collaborate closely with Dr. Yuxin Cao (from NUS).

If you would like to learn more about my work, feel free to check out my recent publications below or contact me directly.

Publications

• Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
  Weifei Jin, Junjie Su, Hejia Wang, Yulin Ye, Jie Hao.
  To appear in IEEE International Conference on Multimedia & Expo (ICME), 2025.

• Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
  Weifei Jin, Yuxin Cao, Junjie Su, Derui Wang, Yedi Zhang, Minhui Xue, Jie Hao, Jin Song Dong, Yixian Yang.
  To appear in the 34th USENIX Security Symposium (USENIX Security), 2025.

• Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
  Weifei Jin, Yuxin Cao, Junjie Su, Qi Shen, Kai Ye, Derui Wang, Jie Hao, Ziyao Liu.
  In the 2nd ACM Workshop on Secure and Trustworthy Deep Learning Systems (SecTL, AsiaCCS Workshop), 2024, pp. 47–55.

News

• 03/2025: Our paper on boosting the transferability of audio adversarial examples was accepted by ICME 2025.
• 01/2025: Our paper on speech privacy protection against eavesdroppers was accepted by USENIX Security 2025.
• 09/2024: We successfully received funding from the Beijing Natural Science Foundation Undergraduate “QiYan” Program.
• 04/2024: Our paper on audio adversarial attacks was accepted by SecTL 2024 (AsiaCCS Workshop).

Projects

Beijing Natural Science Foundation Undergraduate “QiYan” Program (2024–2026, expected)

• Principal Investigator
• Focused on leveraging latent space features for adversarial perturbations on automatic speech recognition (ASR) systems
• Aim to enhance the security and robustness of ASR through novel defense and attack methodologies

National Undergraduate Innovation and Entrepreneurship Training Program (Jun 2023 – May 2024)

• Core Member in a national-level research project
• Focused on adversarial attacks and defenses in speech recognition based on style transfer
• Led the publication of an adversarial attack paper at SecTL 2024

Awards

• Second-Class Scholarship, Beijing University of Posts and Telecommunications (2024)
• “Merit Student”, Beijing University of Posts and Telecommunications (2024)
• Second Prize, 9th National Cryptography Technology Competition (2024)
• Rank 1st in GPA in the major for two consecutive academic years

Services

• Academic Reviewing: Served as a reviewer for ICME 2025, WWW 2024.
• Mentoring: Guided junior students in Cyberspace Security projects focusing on adversarial attacks.