116-Page Paper Reveals LLM API Flaw: Hidden Reasoning Traces Can Be Fully Extracted

A paper reveals a design flaw in frontier LLM APIs that allows attackers to extract fully encrypted hidden reasoning chains. The vulnerability affects major vendors like Anthropic, OpenAI, and Google, exploiting security weaknesses in weaker models within the same family to achieve cross-model reasoning extraction. The study verified extraction accuracy via API billing token counts, sparking widespread community attention.