Test-time policy shaping aligns autonomous cyber defense agents
In CybORG, adaptive shaping improved CIA alignment without retraining while keeping defense performance.
2 stories, newest first · one card per story
In CybORG, adaptive shaping improved CIA alignment without retraining while keeping defense performance.
Automated defensive actions would be allowed only when bounded, interruptible, recoverable, and reconstructable from evidence.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views