Evaluating Security Risk in DeepSeek and Other Frontier Reasoning Models

Evaluating Security Risk in DeepSeek and Other Frontier Reasoning Models

This original research is the result of close collaboration between AI security researchers from Robust Intelligence, now a part of Cisco, and the University of Pennsylvania including Yaron Singer, Amin Karbasi, Paul Kassianik, Mahdi Sabbaghi, Hamed Hassani, and George Pappas. Executive Summary This article investigates vulnerabilities in DeepSeek R1, a new frontier reasoning model from Chinese AI startup DeepSeek. It has gained global attention for its advanced reasoning capabilities and cost-efficient training method. While its…

Read More