● AI WORKSHOP
Offensive AI:
A hands-on
Red Team intensive
Learn how modern AI systems are attacked through realistic, hands-on labs covering LLMs, AI agents, tools, and the emerging AI attack surface. Built for penetration testers, red teamers, offensive security engineers, consultants and AI/ML engineers.
Cyber Helmets and Zero Lab are collaborating to develop and deliver an intensive hands-on online workshop focused on offensive AI security, featuring realistic attack scenarios, immersive labs, and practical techniques for assessing modern AI systems.
Join to learn:
- How AI is changing common attack vectors across organizations
- Real examples of prompt injection, phishing, and AI-enabled social engineering scenarios
- Risks introduced by AI tools and AI agent adoption
- Common blind spots organizations face around AI adoption
- Practical ways organizations can improve awareness and readiness around AI-related threats
● WHAT YOU’LL DO
What you’ll work on
Embedded protocol analysis & adversarial workflows
Decode and analyze embedded communication protocols to understand real-world attacker workflows.
Logic capture & dynamic behavior analysis
Analyze communication traces and dynamic behavior using a simulated hardware environment.
Embedded communication analysis
Analyze device communication logic to understand behavior, data flows, and system interactions.
Hardware analysis & component identification
Showcase real hardware workflows used to identify and access hardware interfaces and components on embedded devices.
Repeatable embedded analysis methodology
Develop a repeatable methodology for approaching and analyzing embedded protocols across different hardware devices.
Practical takeaways & reusable tooling
Leave with practical notes, reusable tooling, and a clear action plan for applying these techniques in real security assessments.
● AGENDA
Your 2-day training journey
Day 1
Understanding embedded communication through an attacker’s lens
→ Digital signal fundamentals for embedded communication
→ Protocol behavior patterns
→ Decoding embedded protocol captures
→ Reversing simple serial communication flows
→ Guided hands-on labs analyzing real-world communication scenarios
Day 2
Practical exploitation of embedded interfaces
→ Identifying and accessing hidden or undocumented hardware interfaces
→ Escaping restrictive debugging environments
→ Retrieving and analyzing embedded firmware
→ Discovering credentials and sensitive information stored on devices
→ Achieving persistence through hardware-level techniques
→ Demonstrating debugging workflows to support deeper device analysis
→ Analyzing unknown and undocumented data formats
● INSTRUCTORS
Meet the instructors
Pete McKernan
AI Security – Offensive Applications and AI Enabled Attack/Defend | HTB Fed Enterprise #1 // Omni Top 100
● WHAT YOU’LL GAIN
Key takeaways
→ A deep understanding of embedded communication protocols and how they are used in hardware devices.
→ Hands-on experience analyzing embedded protocols using real-world captures and signals.
→ The ability to extract sensitive information from IoT devices through hardware-level analysis
→ Confidence in identifying and assessing hardware interfaces on embedded devices.
→ The skills to analyze real-world attacker workflows when assessing the security of IoT and embedded systems.
● REQUIREMENTS & PREREQUISITES
Requirements
→ Create an HTB account in advance (VIP+ access provided as part of the workshop)
→ Basic familiarity with Linux command-line workflows.
→ A general understanding of how embedded devices communicate (high-level only, no hardware experience required).
→ Experience with hands-on problem solving in a technical environment such as debugging, scripting, or working with protocol/data formats.
→ Comfort installing and running lightweight tooling used for viewing traces, interacting with simulated hardware, and performing analysis.
● BOOK YOUR SEAT
Step into the arena
Join us for two days of hands-on embedded protocol analysis and exploitation.
Book your seat
What's included:
- 2 days (6h/day) of live expert-led instruction with real hardware demonstrations and attacker-focused guidance
- Real examples of deepfake, phishing, and AI-enabled social engineering scenarios
- Risks introduced by unsafe AI tools and AI agent usage
- Common blind spots organizations face around AI adoption
- Practical ways organizations can improve awareness and readiness around AI-related threats
