- Cisco bolsters DNS security package
- 10 must-try Google Photos tips and tricks - including a new AI editor
- AI could erase half of entry-level white collar jobs in 5 years, CEO warns
- Is all this data about our health good for our health?
- Why I prefer this Lenovo tablet over the iPad for multimedia consumption - and it's $130 off
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