Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

Always Day One

12 minute read

Published:

In 2012, Jeff Bezos wrote in his annual letter to Amazon shareholders: “Day 2 is stasis, followed by irrelevance, followed by excruciating painful decline, followed by death.” He used “Day One” to describe a state of perpetual beginning—curious, disruptive, restless. Years later, ByteDance adopted this philosophy as the first principle of its corporate culture: Always Day One.

Finding My Way

11 minute read

Published:

Today, I’ve decided to start writing blogs again—or perhaps to start properly for the first time. Three years ago, as a freshman at Beijing University of Posts and Telecommunications, I kept a site at momoyeyu.github.io. But those posts were closer to study notes than real writing. So here, on March 31, 2025, I’m starting over.

portfolio

publications

Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer

Published in SecTL 2024 (AsiaCCS Workshop), 2024

In the 2nd ACM Workshop on Secure and Trustworthy Deep Learning Systems (SecTL, AsiaCCS Workshop), 2024, pp. 47–55.

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

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems

Published in USENIX Security 2025, 2025

In the 34th USENIX Security Symposium (USENIX Security), 2025.

Recommended citation: Weifei Jin, Yuxin Cao, Junjie Su, Derui Wang, Yedi Zhang, Minhui Xue, Jie Hao, Jin Song Dong, and Yixian Yang. 2025. "Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems." In 34th USENIX Security Symposium, to appear.
Download Paper

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio–Language Models

Published in NeurIPS 2025, 2025

In the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.

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

talks

teaching