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 joint research effort led by Alexander Panfilov (University of Tübingen), Florian Tramer (ETH Zürich), Yarin Gal (Oxford), and Kyle Miller (Center for Security and Emerging Technologies) has uncover…
A German research team from the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems has demonstrated a simple replay attack that extracts hidden reasoning traces from proprie…
Security researchers from MATS Research, the ELLIS Institute Tübingen, the Max Planck Institute for Intelligent Systems, and Snyk found that Anthropic, OpenAI, and Google use a single global encryptio…
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.…
Researchers led by Alexander Panfilov have disclosed a vulnerability in proprietary LLM APIs from Anthropic, OpenAI, and Google that allows attackers to decrypt hidden chain-of-thought reasoning trace…