Machine Learning Street Talk (MLST)//Alexander Panfilov
Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov
Ilia Shumailov and Alexander Panfilov describe a cross-vendor attack on proprietary LLM reasoning APIs where encrypted reasoning traces can be replayed, decoded, and repurposed across users and sibling models. They argue the issue is fundamentally a jailbreak and privacy problem, with possible defenses ranging from not exposing reasoning at all to tighter replay binding and trace detection.
