Offense vs. Defense in the Age of AI | Red Team vs. Blue Team Panel
Who has the edge in AI security when attackers and defenders have the same models? In this red team vs. blue team panel, Teleport's Ben Arent (Director of Product) talks with Rob (Director of Security, Teleport) and Marcus (founder, maker of Nemesis) about how AI is reshaping infrastructure security: frontier models like Mythos, the Hugging Face incident, prompt injection and the "lethal trifecta," alert fatigue in the SOC, and Teleport's "Pressure Washing" project, where 13 engineers spent a quarter hunting vulnerabilities with LLMs and found more high-severity bugs than in 2024 and 2025 combined.
Recorded live in New York City.
⏱️ Chapters
00:00 Intro
01:58 First systems they broke into
03:44 Red team, blue team, purple team
06:00 How the security industry has changed
08:33 The biggest shift since LLMs
10:40 The Hugging Face incident
13:38 What keeps you up at night?
14:04 Frontier models: hype vs. reality
18:10 Prompt injection and the lethal trifecta
19:51 Defending against shadow AI inside your company
21:19 Can AI replace your security team?
23:11 AI in GRC
23:53 Can you fully automate a red team?
25:51 Pressure Washing: 13 engineers, one quarter, LLM vuln hunting
28:32 Property-based testing and formal verification
30:02 Property-based testing for infrastructure (Nemesis)
32:01 AI vs. AI: where is the edge?
33:15 Alert fatigue and the AI SOC
34:54 One takeaway from each panelist
📝 Read the Pressure Washing blog post: https://goteleport.com/blog/finding-vulnerabilities-with-llms/
- ️ More Teleport security talks: https://goteleport.com/resources/
- 🔔 Subscribe for more on identity and infrastructure security.
🔗 Learn more about Teleport: https://goteleport.com
🔗 Learn more about Nemesis: https://www.persistent-security.net
🐦 Follow us: https://x.com/goteleport
#cybersecurity #AI #redteam