Welcome to Lina's Homepage

Lina Alkarmi

Lina Alkarmi

Ph.D. Candidate

Department of Electrical Engineering and Computer Science
University of Michigan, Ann Arbor

Address: 1301 Beal Ave, Ann Arbor, MI, USA, 48105
E-mail: lalkarmi [at] umich [dot] edu

About Me

I am a third-year Ph.D. student at the University of Michigan, Ann Arbor, where I am fortunate to be advised by Prof. Mingyan Liu. My research sits at the intersection of mechanism design, security economics, and strategic machine learning.

Broadly, I study how institutional systems shape human behavior and how to redesign them to promote honest participation. On the theoretical side, I work on strategic classification and mechanism design, asking how algorithmic decision systems can be made robust to agents who game them, and how incentive mechanisms can be designed so that honest behavior is also the rational choice. On the empirical side, I study security economics, measuring the social cost of data breaches and their downstream effects on identity theft victims.

I am fortunate to be supported by an NSF Graduate Research Fellowship. Before coming to Michigan, I received my B.S. in Electrical Engineering from George Mason University, and spent time at MIT working on Bayesian filtering in chaotic systems.

Research Interests

Mechanism Design • Security Economics • Strategic Classification

Publications

  1. Understanding Federated Learning Through the Lens of Mechanism Design: The Role of Data Heterogeneity
    Lina Alkarmi*, Po-Yen Chen*, and Mingyan Liu.
    International Conference on Game Theory and AI for Security (GameSec), 2026. (* Equal Contribution)
    [arXiv]
    [BibTeX] 
    @misc{alkarmi2026understandingfederatedlearninglens,
  title={Understanding Federated Learning Through the Lens of Mechanism Design: The Role of Data Heterogeneity},
  author={Lina Alkarmi and Po-Yen Chen and Mingyan Liu},
  year={2026},
  eprint={2608.00364},
  archivePrefix={arXiv},
  primaryClass={cs.GT},
  url={https://arxiv.org/abs/2608.00364}
}
  2. Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
    Ziyuan Huang*, Lina Alkarmi*, and Mingyan Liu.
    International Conference on Machine Learning (ICML), 2026. (* Equal Contribution)
    [arXiv]
    [BibTeX] 
    @article{huang2026multilevel,
  title={Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics},
  author={Huang, Ziyuan and Alkarmi, Lina and Liu, Mingyan},
  journal={arXiv preprint arXiv:2602.11439},
  note={Appeared at ICML 2026},
  year={2026}
}
  3. Estimating the Social Cost of Corporate Data Breaches
    Lina Alkarmi, Armin Sarabi, and Mingyan Liu.
    Workshop on the Economics of Information Security (WEIS), 2026.
    [arXiv]
    [BibTeX] 
    @article{alkarmi2026estimating,
  title={Estimating the Social Cost of Corporate Data Breaches},
  author={Alkarmi, Lina and Sarabi, Armin and Liu, Mingyan},
  journal={arXiv preprint arXiv:2603.21270},
  note={Appeared at WEIS 2026},
  year={2026}
}
  4. When In Doubt, Abstain: The Impact of Abstention on Strategic Classification
    Lina Alkarmi, Ziyuan Huang, and Mingyan Liu.
    International Conference on Game Theory and AI for Security (GameSec), 2025.
    [Proceedings] [arXiv]
    [BibTeX] 
    @inproceedings{alkarmi2025abstain,
  title={When In Doubt, Abstain: The Impact of Abstention on Strategic Classification},
  author={Alkarmi, Lina and Huang, Ziyuan and Liu, Mingyan},
  booktitle={International Conference on Game Theory and AI for Security (GameSec)},
  pages={124--144},
  year={2025}
}

Professional Services

  • Graduate Student Engineering Ambassador (GSEA): University of Michigan, May 2026 to Present
  • Conference Reviewer: ICML 2026, NeurIPS 2026, GameSec 2026