Boffins bust AI with corrupted training data • The Register
If you don’t know what your AI model is doing, how do you know it’s not evil? Boffins from New York University have posed that question in a paper at arXiv, and come up with the disturbing conclusion that machine learning can be taught to include backdoors, by attacks on their learning data. The problem of a “maliciously trained network” (which they dub a “BadNet”) is more than a theoretical…