IBM finds a way to watermark AI’s to protect them from theft and sabotage

IBM finds a way to watermark AI’s to protect them from theft and sabotage

WHY THIS MATTERS IN BRIEF Creating complex neural networks and AI’s takes a lot of expertise, money and resources so being able to watermark them will help protect them from theft.   What if machine learning models, much like photographs, movies, music, and manuscripts, could be watermarked nearly imperceptibly to denote...

Read more