FLOP: Breaking the Apple M3 CPU via False Load Output Predictions

Jason Kim, Jalen Chuang, Daniel Genkin, Yuval Yarom

34th USENIX Security Symposium · Day 1

This article delves into "FLOP: Breaking the Apple M3 CPU via False Load Output Predictions," a significant research paper presented at USENIX Security. The work, authored by Jason Kim, Jalen Chuang, and Daniel Genkin from Georgia Tech, and Yuval Yarom from Ruhr University Bochum, uncovers a novel microarchitectural vulnerability stemming from a **Load Value Predictor (LVP)** implemented in recent Apple M- and A-series processors, including the M3, M4, and A17 Pro. This LVP, a performance optimization designed to mitigate Read-After-Write (RAW) dependencies, is shown to introduce critical security flaws by speculatively computing on stale or incorrect data values.

AI review

This is the real deal — novel hardware vulnerability research on Apple's newest silicon, reverse-engineered from scratch, with two end-to-end browser exploits leaking actual user data. The kind of work that forces Apple to patch and makes every other CPU vendor sweat about their own value predictors.