Your Model’s Memory Has Been Compromised: Adversarial Hubness in RAG Systems Idan Habler on March 12, 2026 at 4:00 pm
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 […]
[#item_full_content] 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 Read More Cisco Blogs
