Cisco/TD Ai Defense Workshop

AI Defense: Chicago

Cisco's AI Defense Workshop covers how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks
• Side-by-side testing of Monitor and Enforce policy modes using the AI Defense Demo Runner

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety

Netsync AI Defense Workshop

Cisco's AI Defense Workshop covers how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks
• Side-by-side testing of Monitor and Enforce policy modes using the AI Defense Demo Runner

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety

Grand Rapids - AI Defense Workshop

Cisco's AI Defense Workshop covers how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks
• Side-by-side testing of Monitor and Enforce policy modes using the AI Defense Demo Runner

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety

2026.11.12 AI Defense Product Workshop - EMEA

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

AI Cyber Defense: Memphis

Cisco's AI Defense Workshop covers how to utilize "Discovery, Detection, and Protection"—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety

Date: Nov 16th, 2026
Time: 11:00AM - 2:00PM CST
Location: University of Memphis, FedEx Institute of Technology: RM 203/205 Fishbowl

AI Defense Workshop - Nov2026

AI Defense Workshop

AI systems are probabilistic and require different security controls than deterministic software. This course shows you how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. You will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

Learning roadmap

2026.11.18 AI Defense Product Workshop - APJC

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

Ritz Carlton - AI Defense

Cisco's AI Defense Workshop covers how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks
• Side-by-side testing of Monitor and Enforce policy modes using the AI Defense Demo Runner

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety

2026.12.02 AI Defense Product Workshop - AMER

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

AI Defense Workshop

Cisco AI Defense Workshop

Dove: 

3 dicembre, 10:00- 17:00 

Co-Innovation Center Cisco, via san Vittore 21, Milano 

Attività: 

10:00-13:00 Dalla AI Agentica alla protezione delle applicazioni AI

•I rischi della sicurezza AI:  le nuove minacce introdotte dall’AI generativa e agentica e i limiti delle soluzioni di sicurezza tradizionali.
• La visione di Cisco. AI for Security e Security for AI.
• Protezione dallo Shadow AI e dal traffico AI malevolo: AI Access.
• DefenseClaw, inspection, enforcement and audit on the agent endpoint.
• Cisco AI Defense: proteggere applicazioni, modelli e agenti AI lungo l’intero ciclo di vita.
• Sicurezza dei modelli AI:  AI Validation e tecniche di Algorithmic Red Teaming.
• AI Supply Chain: vulnerabilità e minacce attraverso Model Scanning e MCP Server Scanning.
• Protezione Runtime:  policy e guardrail per LLM e workflow agentici.

13:00-14:00 Lunch

14:00-17:30 Laboratori:

• Cisco AIDefense workshop Labs

2026.12.15 AI Defense Workshop - Atlanta

professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Product Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

2026.12.15 AI Defense Workshop - Atlanta

professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Product Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

2026.12.15 AI Defense Product Workshop - AMER

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

2027.01.12 AI Defense Product Workshop - EMEA

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

2027.01.19 AI Defense Product Workshop - AMER

Secure the AI Era with an immersive, instructor-led workshop designed to help security professionals understand, assess, and defend against the unique risks introduced by generative and agentic AI.

In this Cisco AI Defense Virtual Workshop, you’ll step into the role of an AI Security Specialist and take on the challenge of securing AI across the enterprise. Through real-world scenarios, you’ll discover AI assets, validate models through algorithmic red teaming, identify hidden threats in AI models, and build security policies that protect AI applications in real time. You’ll also explore emerging agentic AI risks, including prompt injection, tool poisoning, and rug pull attacks.

What you’ll do:

• Discover and monitor AI assets across enterprise environments
• Scan your AI supply chain for embedded threats and vulnerabilities
• Test the security of your models and agents with algorithmic red teaming
• Build and enforce runtime policies that block security threats, sensitive data exposure, and other harmful behaviors

Cisco Ready To Fly - AI Defense Workshop MCR

Cisco's AI Defense Workshop covers how to use the Cisco 3-step framework—Discovery, Detection, and Protection—to secure the AI lifecycle. Participants will practice running algorithmic red teaming simulations, scanning model files for malicious payloads, and configuring runtime guardrails. The workshop also covers securing agentic workflows using the Model Context Protocol (MCP) to prevent goal hijacking and context poisoning.

What to expect

You will work through the workshop as a Senior Security Engineer at PseudoCo, a fictional organization deploying generative and agentic AI across its enterprise. The workshop covers four use cases and fifteen success criteria.

The workshop includes:

• AI asset discovery using Cisco AI Defense
• Algorithmic red teaming to test models for prompt injection, jailbreaking, and harmful content generation
• Model file scanning for embedded threats in .pkl, .h5, and .onnx files
• Runtime policy configuration to block PII, PHI, and PCI data leaks
• MCP server scanning for vulnerabilities and intent-based threats
• Agentic protection against tool poisoning, prompt injection, and rug pull attacks
• Side-by-side testing of Monitor and Enforce policy modes using the AI Defense Demo Runner

Who should attend

• Security engineers and architects
• AI and ML platform owners
• Application security teams
• IT and security leaders responsible for AI governance

What you will learn

• How Cisco AI Defense applies the Discovery, Detection, and Protection framework to AI systems
• How to validate models before deployment and protect them at runtime
• How to detect and block agentic AI threats specific to MCP-based architectures
• How to build runtime policies that enforce data protection and content safety