Hongwei Li

BioMoTouch is a multi-modal touch authentication framework that jointly models physiological contact structures (from capacitive screens) and behavioral motion dynamics (from inertial sensors) to achieve high accuracy and robustness in touch-based authentication.

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and defense mechanisms.

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a significant and often overlooked copyright risk.

The paper introduces ExploitGym, a large-scale benchmark, demonstrating that advanced AI agents can successfully turn theoretical software vulnerabilities into working exploits, highlighting growing cybersecurity risks.