I am an incoming M.S. student in Intelligent Science and Technology at Beijing University of Posts and Telecommunications (BUPT), where I also received my B.E. in Cyberspace Security (Experimental Class). My research interests include AI Agents, Trustworthy AI and System Architecture.

Starting Fall 2026, I will join Prof. Jun Liu’s group. Previously, I worked with Prof. Jie Hao on Audio Security and Adversarial Machine Learning. Currently, I am at MiroFish (Shanda Group) as an AI Intern & Founding Member.

News

• 01/2026: Joined MiroFish (Shanda Group) as an AI Intern & Founding Member.
• 11/2025: Won First Prize at the Global Campus AI Algorithm Elite Competition.
• 10/2025: We released a paper on adversarial attacks against polyphonic sound event detection systems on arXiv.
• 09/2025: Admitted to BUPT M.S. program in Intelligent Science and Technology.
• 09/2025: Our paper on guardrails for audio-language models was accepted to NeurIPS 2025.
• 08/2025: Won First Prize at the National College Students Information Security Contest.
• 07/2025: Joined ByteDance as Backend R&D Intern at TikTok-Servarch-Cost&Performance.
• 04/2025: Won Bronze Award at the China International College Students’ Innovation Competition.
• 03/2025: Our paper on transferability of audio adversarial examples was accepted to ICME 2025.
• 01/2025: Our paper on speech privacy protection was accepted to USENIX Security 2025.
• 11/2024: Won Second Prize at the National Cryptography Technology Competition.
• 04/2024: Our paper on robustness of ASR systems was accepted to SecTL 2024 (AsiaCCS Workshop).

Publications

• ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models Weifei Jin, Yuxin Cao, Junjie Su, Minhui Xue, Jie Hao, Ke Xu, Jin Song Dong, Derui Wang. In the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.

• Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems Junjie Su, Weifei Jin, Yuxin Cao, Derui Wang, Kai Ye, Jie Hao. arXiv preprint, 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. In the 34th USENIX Security Symposium (USENIX Security), 2025.

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

Work Experience

Shanda Group — MiroFish (AI Startup) AI Intern & Founding Member & Team Lead — Jan 2026 – Present

ByteDance Backend R&D Intern — TikTok-Servarch-Cost&Performance — Jul 2025 – Dec 2025

Antiy Technology Group Co., Ltd. Security Development Intern — Technical Committee — Jul 2024 – Aug 2024

Student Work

BUPT Table Tennis Association President — Sept 2023 – Jul 2024 Core Member — Sept 2022 – Jul 2023

Scholarships & Awards

• 2025 Global Campus AI Algorithm Elite Competition — First Prize
• 2025 National College Students Information Security Contest — First Prize
• 2024 China International College Students’ Innovation Competition — Bronze Award
• 2024 National Cryptography Technology Competition — Second Prize