About me

Hello! I am a Senior Security Researcher at the Microsoft Security Response Center (MSRC). As part of the V&M AI group, I assess vulnerabilities affecting Microsoft’s AI products and further Microsoft’s research into AI Security.

Before joining Microsoft, I was a Security Researcher in Intel’s Security Assurance and Cryptography group. You can read about some of the work we did on addressing the unique security challenges posed by integrated AI agents on arXiv.

My Ph.D. advisor was Chris Fletcher at the University of Illinois at Urbana-Champaign. My graduate research performed the first broad, systematic study of the microarchitecture literature to characterize the security implications of both known and new (theorized) microarchitectural optimizations [1]. To facilitate this study, we developed a novel abstraction to precisely and concisely capture potential leakage while abstracting away the victim program and threat model. This study discovered, for the first time, that microarchitecture outside of speculative instruction execution is capable of forming a “universal read gadget” (URG). A variant of this microarchitecture was subsequently discovered in Apple silicon, which proved to be the first microarchitecture (in the wild) capable of leaking data at rest [2].

You can learn more about this second work, Augury, at prefetchers.info! Here’s a twitter thread about it too. Our experiments demonstrate the existence of a pointer-chasing DMP on recent Apple processors, including the A14 and M1. We then reverse engineer the details of this DMP to determine the opportunities for and restrictions it places on attackers using it. Finally, we demonstrate several basic attack primitives capable of leaking pointer values using the DMP.

I received my B.S. from Lawrence Technological University (in Southfield, MI), where I was a two time recipient of a Presidential Research Grant. I went on to complete my M.S. at the University of Illinois at Urbana-Champaign in the fall of 2019. My M.S. culminated in the introduction of Asynchronous Poisoning Attacks.

Feel free to contact me jose.sanchezvicarte [at] microsoft [dot] com with any questions about my papers, research, or anything else.