
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.
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!
Otros episodios de "Embedded AI - Intelligence at the Deep Edge"



No te pierdas ningún episodio de “Embedded AI - Intelligence at the Deep Edge”. Síguelo en la aplicación gratuita de GetPodcast.








