Zero Trust in the Era of Agentic AI

AI agents use the same networking infrastructure as users and apps. So security solutions like zero trust should evolve to protect agentic AI communications.

Detecting Exposed LLM Servers: A Shodan Case Study on Ollama

We uncovered 1,100+ exposed Ollama LLM servers—20% with open models—revealing critical security gaps and the need for better LLM threat monitoring.

Foundation-sec-8B-Instruct: An Out-of-the-Box Security Copilot

Foundation-sec-8B-Instruct layers instruction fine-tuning on top of our domain-focused base model, giving you a chat-native copilotthat understands security.

Cisco’s Foundation AI Advances AI Supply Chain Security With Hugging Face

Cisco's Foundation AI is partnering with Hugging Face, bringing together the world's leading AI model hub with Cisco's security expertise.

Securing an Exponentially Growing (AI) Supply Chain

Foundation AI's Cerberus is a 24/7 guard for the AI supply chain, analyzing models as they enter HuggingFace and sharing results to Cisco Security products.

Cisco Contributes to Cyber Hard Problems Report

Cisco contributes to the latest edition of the Cyber Hard Problems report, highlighting 10 foundational security challenges facing the modern world.

Making Agentic AI Work in the Real World

Cisco is extending the principles of zero trust to Agentic AI. Cisco's Universal Zero Trust Network architecture gives you the tools you need.

Foundation-sec-8b-reasoning: World’s First Security Reasoning Model

Foundation AI's second release—Foundation-sec-8b-reasoning is designed to designed to bring enhanced analytical capabilities to complex security workflows.

Market-Inspired GPU Allocation in AI Workloads: A Cybersecurity Use Case

Learn how a self-adaptive GPU allocation framework that dynamically manages the computational needs of AI workloads of different assets/systems.

Foundation-sec-8b: Cisco Foundation AI’s First Open-Source Security Model

Foundation AI's first release — Llama-3.1-FoundationAI-SecurityLLM-base-8B — is designed to improve response time, expand capacity, and proactively reduce risk.

Foundation AI: Robust Intelligence for Cybersecurity

Foundation AI is a Cisco organization dedicated to bridging the gap between the promise of AI and its practical application in cybersecurity.

Cisco Co-Authors Update to the NIST Adversarial Machine Learning Taxonomy

Cisco and the UK AI Security Institute partnered with NIST to release the latest update to the Adversarial Machine Learning Taxonomy.

Cisco Introduces the State of AI Security Report for 2025: Key Developments, Trends, and Predictions in AI Security

Cisco is proud to share the State of AI Security report covering key developments in AI security across threat intelligence, policy, and research.

AI Threat Intelligence Roundup: February 2025

AI threat research is a fundamental part of Cisco’s approach to AI security. Our roundups highlight new findings from both original and third-party sources.

AI Cyber Threat Intelligence Roundup: January 2025

AI threat research is a fundamental part of Cisco’s approach to AI security. Our roundups highlight new findings from both original and third-party sources.

Evaluating Security Risk in DeepSeek and Other Frontier Reasoning Models

The performance of DeepSeek models has made a clear impact, but are these models safe and secure? We use algorithmic AI vulnerability testing to find out.

Cisco AI Defense: Comprehensive Security for Enterprise AI Adoption

Cisco AI Defense is a single, end-to-end solution that helps your organization understand and mitigate risk on both the user and application levels.

Advancing AI Security and Contributing to CISA’s JCDC AI Efforts 

Discover how CISA's new AI Security Incident Collaboration Playbook strengthens AI security and resilience.