Author

Alexander Panfilov

Max Planck Institute for Intelligent Systems

h-index 6 Homepage View on Semantic Scholar

We have 1 of 16 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Stealing Reasoning Traces from Proprietary LLM APIs

An architectural vulnerability is identified that circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as well as proposing concrete cryptographic and system-level mitigations to secure client-side reasoning.

Alexander Panfilov, David Schmotz, I. Shumaĭlov et al. · 4 citations · ⚡2