AI Safety

All Work

Five ways IBM is using synthetic data to improve AI models
Five ways IBM is using synthetic data to improve AI models
IBM Research
Explained: How to tell if artificial intelligence is working the way we want it to
Explained: How to tell if artificial intelligence is working the way we want it to
MIT News
A safer, lower-cost alternative to real data for pretraining computer vision models
A safer, lower-cost alternative to real data for pretraining computer vision models
IBM Research blog
Keeping web-browsing data safe from hackers
Keeping web-browsing data safe from hackers
MIT News
AI model to detect anomalies in power grid failures
AI model to detect anomalies in power grid failures
India Next
Cars require regular inspection, why should AI models be any different?
Cars require regular inspection, why should AI models be any different?
Technology Networks
The man who challenges AI every day
The man who challenges AI every day
IBM Research
Chuchu Fan designs safe and reliable autonomous systems
Chuchu Fan designs safe and reliable autonomous systems
MIT ILP
Demystifying machine-learning systems
Demystifying machine-learning systems
MIT News
AI Researchers Fight Noise by Turning to Biology
AI Researchers Fight Noise by Turning to Biology
Quanta Magazine
Securing AI systems with adversarial robustness
Securing AI systems with adversarial robustness
IBM Research Blog
Machines that see the world more like humans do
Machines that see the world more like humans do
MIT News
Is neuroscience the key to protecting AI from attack?
Is neuroscience the key to protecting AI from attack?
VentureBeat