I sadly missed @zicokolter
's talk, but I really vibed w/ one of his punchlines he shared w/ me today: adversarial robustness may be a basic and toy problem, but we still haven't solved it. Inability to do this indicates gaps in our knowledge, which underlie more complex settings. https://
x.com/NicolasPaperno
/NicolasPapernot/status/1623324869000667137
…
Adversarial Robustness: Fundamental Problem Underpinning AI Safety
By
–
Leave a Reply