[Paper] “Unsolved Problems in ML Safety” by Dan Hendrycks, Nicholas Carlini, John Schulman and Jacob Steinhardt

AI Safety Newsletter · Aug 21, 2023 · 53m

Machine learning (ML) systems are rapidly increasing in size, are acquiring new capabilities, and are increasingly deployed in high-stakes settings. As with other powerful technologies, safety for ML should be a leading research priority. In response to emerging safety challenges in ML, such as those introduced by recent large-scale models, we provide a new roadmap for ML Safety and refine the technical problems that the field needs to address. We present four problems ready for research, namely withstanding hazards (“Robustness”), identifying hazards (“Monitoring”), steering ML systems…