All Blogs

Blog post

Your Model’s Memory Has Been Compromised: Adversarial Hubness in RAG Systems

This blog is jointly written by Amy Chang, Idan Habler, and Vineeth Sai Narajala. Prompt injections and jailbreaks remain a major concern for AI security, and for good reason: models remain susceptible to users tricking models into doing or saying things like bypassing guardrails or leaking system prompts. But AI deployments don’t just process prompts […]

Blog post

Cisco optical innovations deliver resilient, scalable, efficient AI networking

AI is driving exponential growth in network bandwidth, reach, and power efficiency requirements. The Cisco optical portfolio meets these needs with resilient, scalable, and power-efficient solutions, ready for hyperscalers, neoscalers, and service providers who are deploying the next generation of AI and cloud applications.