Embedded AI - Intelligence at the Deep Edge podcast

AI Exposes Unpatchable Smart Devices

0:00
18:59
Spola tillbaka 15 sekunder
Spola framåt 15 sekunder

Send us Fan Mail

What happens when vulnerability discovery scales with compute, but remediation remains trapped in the physical supply chain?

In this episode, we dive into a landmark study from Forescout’s Vedere Labs, where an off-the-shelf AI harness—combining generally available Claude models with Ghidra, Semgrep, and Joern—uncovered 99 confirmed vulnerabilities (66 of them brand-new) across 10 embedded TCP/IP stacks in roughly 90 hours for just US$2,300. Five years earlier, the manual baseline (Project Memoria) required 18 months of research and nine months of manual code review to find a comparable 97 flaws.

While discovery has been radically repriced by token budgets, remediation cannot be bought by the token. From orphaned hardware—like a discontinued wireless access point carrying seven device-specific flaws that "no one will ever fix"—to the 20-year tail of legacy supply chains, we examine why the vulnerability backlog is crossing a structural threshold. Drawing lessons from biological defense (avoidance, resistance, and tolerance), we explore how embedded engineers must design for survivability when a patch may never arrive.

Support the show

If you are interested in learning more then please subscribe to the podcast or head over to https://medium.com/@reefwing, where there is lots more content on AI, IoT, robotics, drones, and development. To support us in bringing you this material, you can buy me a coffee or just provide feedback. We love feedback!

Fler avsnitt från "Embedded AI - Intelligence at the Deep Edge"