4 min read

Today, Cisco launched the LLM Security Leaderboard, a comprehensive resource for evaluating model risk and susceptibility to adversarial attacks. By providing transparent, adversarial evaluation signals, this leaderboard contextualizes model performance metrics against evaluations of how models handle malicious prompts, jailbreak attempts, and other manipulation strategies. The tool empowers organizations with a clear, objective understanding of model risk by mapping threats to our AI Safety and Security Framework taxonomy, and informs defense-in-depth approaches to AI deployments.  

4 min read

We recently discovered a method to compromise Claude Code’s memory and maintain persistence beyond our immediate session into every project, every session, and even after reboots. In this post, we’ll break down how we were able to poison an AI.....

3 min read

Thank you to all of the contributors of the State of AI Security 2026, including Amy Chang, Tiffany Saade, Emile Antone, and the broader Cisco AI research team. As artificial intelligence (AI) technology and enterprise AI adoption advance at a rapid pace, the security landscape around it is expanding faster, leaving many defenders struggling to keep […]

1 min read

This blog is jointly written by Amy Chang, Hyrum Anderson, Rajiv Dattani, and Rune Kvist. We are excited to announce Cisco as a technical contributor to AIUC-1. The standard will operationalize Cisco’s Integrated AI Security and Safety Framework (AI Security Framework), enabling more secure AI adoption. AI risks are no longer theoretical. We have seen […]

4 min read

This blog is written in collaboration by Amy Chang, Vineeth Sai Narajala, and Idan Habler Over the past few weeks, Clawdbot (then renamed Moltbot, later renamed OpenClaw) has achieved virality as an open source, self-hosted personal AI assistant agent that runs locally and executes actions on the user’s behalf. The bot’s explosive rise is driven by […]

4 min read

A model context protocol (MCP) tool can claim to execute a benign task such as “validate email addresses,” but if the tool is compromised, it can be redirected to fulfill ulterior motives, such as exfiltrating your entire address book to an external server. Traditional security scanners could flag suspicious network calls or dangerous functions and […]

7 min read

The New Baseline for AI Security  AI is no longer an experimental capability or a back-office automation tool: it is becoming a core operational layer inside modern enterprises. The pace of adoption is breathtaking. Yet, according to Cisco’s 2025 AI Readiness Index, only 29 percent of companies believe they are adequately equipped to defend against […]

6 min read

AI models have become increasingly democratized, and the proliferation and adoption of open weight models has contributed significantly to this reality. Open-weight models provide researchers, developers, and AI enthusiasts with a solid foundation for limitless use cases and applications.  As of August 2025, leading U.S., Chinese, and European models have around 400M total downloads on […]

4 min read

Introduction The pace at which applications for artificial intelligence are evolving continues to impress. Businesses that once considered taking advantage of AI’s sophisticated predictive and natural language capabilities are now evaluating adoption of AI systems that have the ability to access internal data, make complex decisions, and have high levels of autonomy. As we continue […]