Driving Dangerously
April 10, 2019
I've written a few times before about the fragility of neural networks, for example in last year's post Fooling Neural Networks. There is an unstated assumption underlying the training of neural networks that the environment is benign, and there is no adversary trying to fool the neural network. Microsoft started on very limited systems like the original PC, and also assumed a benign environment. Excel had macros, and you could do all sorts of things...like read entries in the contact address book...or send an email...all from within a macro that ran automatically when the spreadsheet was opened. What could possibly go wrong?
To read the full article, click here
Related Semiconductor IP
- nQrux® Root of Trust IP
- AXI to UCIe Bridge IP
- UCIe 2.x Controller IP
- SWI3S (SoundWire I3S Interface) Peripheral Controller Core IP
- OpenTitan-based RISC-V Secure Element
Related Blogs
- What's driving 3D IC design? Do 2D EDA tools need a total overhaul to support 3D design?
- Tabula, Achronix try driving unique design advantages into solidifed FPGA sector
- Safer SoCs for safer driving
- GDDR6 Beyond Graphics : Memory for AI,VR, and Autonomous Driving
Latest Blogs
- From Bug Hunting to Engineering Methodology: Lessons from AI-Driven Development
- Manufacturing Intelligence: Turning EDA Data into Trusted Action
- Execute-in-Place: Getting More from Embedded NVM
- Rethinking RTL flows with AI-driven hybrid formal verification
- Arm and NVIDIA: Building the trusted compute foundation for the agentic AI era