A team from the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems published a paper in August titled "Stealing Reasoning Traces from Proprietary LLM APIs" showing that encr…
Researchers Ilia Shumailov and Alexander Panfilov, speaking on Machine Learning Street Talk, revealed a systemic security flaw in proprietary AI APIs from OpenAI, Anthropic, and Google, demonstrating …
A new paper by Alexander Panfilov, Ilia Shumailov, Luca Beurer-Kellner, Jonas Geiping, Maksym Andriushchenko and colleagues demonstrates that encrypted reasoning traces from proprietary LLM APIs from …
A new preprint, 'Stealing Reasoning Traces from Proprietary LLM APIs,' reveals that encrypted chain-of-thought blocks from Anthropic, OpenAI, and Google can be replayed into weaker sibling models to e…
Researchers Alexander Panfilov, David Schmotz, and Ilia Shumailov found a way to recover encrypted reasoning from models by OpenAI, Anthropic, and Google, as detailed in a paper posted on August 10th.…