In this video, we dive into a real-world Red Team vs. Blue Team scenario. We simulate a cyberattack on a Finance Application that has integrated a new LLM Chatbot. You’ll see firsthand how attackers use Prompt Injection to bypass standard rules, how they move laterally through Kubernetes clusters, and how they attempt to execute Zero Day exploits.

More importantly, we show you how to defend against it. Using Cisco’s Hybrid Mesh Firewall, AI Defense, and Secure Workload, we demonstrate how to:
1. Detect & Block Prompt Injections: safeguarding your LLMs from manipulation.
2. Secure Kubernetes: using micro-segmentation to isolate threats in the cloud.
3. Inspect Encrypted Traffic: utilizing the Encrypted Visibility Engine (EVE) to
spot malware in TLS flows without decryption. 

Whether you are a Network Engineer, Security Analyst, or just interested in how AI is changing the cybersecurity landscape, this demo is packed with practical insights

Big thank you to Cisco for sponsoring my trip to Cisco Live Amsterdam. 

// Ant Ducker SOCIALS // 
LinkedIn:  https://www.linkedin.com/in/ant-ducker-0052801/ 
YouTube channel dCloud:  https://www.youtube.com/@CiscodCloud 

// Website REFERENCE  // 
Cisco Security Cloud control:  https://sign-on.security.cisco.com/ 
Cisco.com:  https://www.cisco.com/site/us/en/solutions/security/hybrid-mesh-firewall/index.html 

// YouTube Video REFERENCE // 
Rick Miles’ video will be linked at a later stage once published. 

// David's SOCIAL //  
Discord: https://discord.com/invite/usKSyzb  
X: https://www.twitter.com/davidbombal  
Instagram: https://www.instagram.com/davidbombal  
LinkedIn: https://www.linkedin.com/in/davidbombal  
Facebook: https://www.facebook.com/davidbombal.co  
TikTok: http://tiktok.com/@davidbombal  
YouTube: https://www.youtube.com/@davidbombal 
Spotify:  https://open.spotify.com/show/3f6k6gERfuriI96efWWLQQ 
SoundCloud:  https://soundcloud.com/davidbombal 
Apple Podcast:  https://podcasts.apple.com/us/podcast/david-bombal/id1466865532 

// MY STUFF // 
https://www.amazon.com/shop/davidbombal  

// SPONSORS //  
Interested in sponsoring my videos? Reach out to my team here: sponsors@davidbombal.com 
 
// MENU // 
0:00 - Coming Up 
01:29 - Intro 
02:20 - Demo Overview 
03:57 - Demo Begins 
09:35 - Adding Guardrails 
11:45 - Secure Workloads 
14:30 - Segmentation Workflow 
18:33 - Overviewing Finance App 
21:02 - Encrypted Visibility Engine 
24:34 - Firewall Obversability and Control 
25:44 - Ant's Advice For The Youth 
26:40 - How to Learn Hybrid Mesh Firewall 
28:16 - Conclusion 

Please note that links listed may be affiliate links and provide me with a small percentage/kickback should you use them to purchase any of the items listed or recommended. Thank you for supporting me and this channel!  

Disclaimer: This video is for educational purposes only.
#cisco #ciscolive  #ciscoemea

David Bombal

A demo walkthrough showing how Cisco's AI Defense product performs automated red teaming against LLM chatbots to detect prompt injection vulnerabilities. The demo covers a finance app with an LLM chatbot deployed on a hybrid cloud/on-prem environment. AI Defense uses algorithmic red teaming to launch thousands of automated attacks against the model, finding that ~69% were blocked natively, then applies guardrails to close the gap. The demo also covers Cisco Secure Workload for microsegmentation and Kubernetes visibility, CVE-based IPS rule synchronization, and the Encrypted Visibility Engine which uses a recurrent neural network to classify TLS flow intent without decryption, including catching zero-day threats via Snort ML.

Hacking LLMs: How to Prevent Prompt Injection Attacks Now