Ulrich Lang
Ulrich Lang received his PhD from Cambridge University Computer
Laboratory (Security Group) on Access Policies for Middleware in 2003
after having completed a Master's in Information Security from Royal
Holloway College (London) in 1997. With 25+ years in infosec, he is a
renowned thought leader in vulnerability analysis of AI, binary
software, 5G, as well as supply chain risk analysis, Zero Trust access
control, and more. He is responsible for the business and technical
strategy, architecture, and direction of ObjectSecurity and its
products. He has published over 150 papers/presentations, 10+ patents,
and was a proposal and project evaluator, Board Member of the Cloud
Security Alliance (Silicon Valley Chapter), conference program
committee, panel moderator, consultant, and book author.
Session
AI models are increasingly delivered as compiled artifacts inside firmware images and native binaries, particularly in IoT, OT, and embedded environments. While these deployment models improve performance and reduce operational dependencies, they also create security blind spots that are poorly understood.
This session examines how AI models can be discovered and analyzed once deployed in embedded systems. The talk focuses on practical reverse engineering techniques used to identify model components, recover structural and behavioral information, and understand the risks introduced by different model packaging and compilation approaches. Attendees will leave with a clearer view of how embedded AI expands the attack surface and why it matters for both offensive and defensive security work.