ML Safety
The ML research community focused on
reducing risks from AI systems.
What is ML Safety?
ML systems are rapidly increasing in size, are acquiring new capabilities, and are increasingly deployed in high-stakes settings. As with other powerful technologies, the safety of ML systems should be a leading research priority. This involves ensuring systems can withstand hazards (Robustness), identifying hazards (Monitoring), reducing inherent ML system hazards (Alignment), and reducing systemic hazards (Systemic Safety). Example problems and subtopics in these categories are listed below:
Robustness
Adversarial Robustness, Long-Tail Robustness
Monitoring
Anomaly Detection, Interpretable Uncertainty, Transparency, Trojans, Detecting Emergent Behavior
Alignment
Honesty, Power Aversion, Value Learning, Machine Ethics
Systemic Safety
ML for Improved Epistemics, ML for Improved Cyberdefense, Cooperative AI
ML Safety Projects
We organize AI/ML safety resources and education for researchers and non-technical audiences.