Michal Yemini

Papers

Total Citations

H-Index

About

Michal Yemini is an emerging researcher whose work sits at the intersection of multi-robot systems, adversarial decision-making, and network security. His research focuses on developing robust frameworks for hypothesis testing in environments where malicious or compromised agents can undermine collective decision-making — a critical challenge as autonomous robot swarms become increasingly deployed in real-world sensing tasks. Yemini's most notable contribution is his resilient binary hypothesis testing framework for adversarial multi-robot crowdsensing, which has garnered 17 citations across its published iterations. This work is particularly innovative in its exploitation of stochastic trust observations between robots, enabling a centralized Fusion Center to make reliable decisions even in the presence of malicious actors — a problem that had previously resisted tractable solutions. By weaving trust dynamics directly into the statistical decision-making process, Yemini bridges the gap between social network theory and robot autonomy. For students and researchers working in distributed sensing, autonomous systems, or adversarial machine learning, Yemini's contributions offer foundational tools for building systems that remain dependable under attack — an increasingly vital property in security-critical deployments of multi-agent robotics.