Sijia Liu
Michigan State University — Computer Science & Engineering · Associate Professor
Research focus: trustworthy ML · adversarial robustness / machine unlearning · optimization for ML · model safety
保护项目第 3 项：构建基于保护项目第 1 项、对抗鲁棒性、无学习遗忘、保护项目第 0、第 2 项、PEFT/LoRA 以及保护项目第 6 项安全性的适配图；请提及一项近期论文或项目，并说明您可在第一学期启动的一项具体扩展。
Who this advisor fits / 什么情况下适合你
- Industry research or startup/translation paths appeal to you (meaningful share in public outcomes).
- High-trajectory trustworthy-ML target; applicants should show robustness/unlearning/optimization depth and ask about first-cohort PhD placement trajectory.
- 工业研究或创业/转化路径对你有吸引力（公开去向里占比不低）。
- 高轨迹可信的ML目标；申请人应展示鲁棒性、无学习遗忘及优化深度，并询问关于第一批次PhD的轨迹。
What to watch for / 什么情况下要慎重
- Faculty-only is your sole goal and you want zero industry/translation exposure.
- 你把「教职为唯一目标」且完全不想碰工业/转化网络。
Public evidence as of 2026-06-10
These are decision-support signals compiled from public evidence (faculty pages, publications, lab sites) to help you ask better questions — not a ranking, rating, or allegation about this advisor. / 以上为基于公开信息整理的择校参考，帮助你提出更好的问题，并非排名、评分或对该导师的指控。
Ask a verified 学长学姐 / 同校 .edu 认证点评
The thing applicants say only 师兄师姐 can tell you — current & former students of this lab, verified by their school .edu. Open the full dossier to read or add a verified note.