ThreatCore: A Benchmark for Explicit and Implicit Threat Detection

The episode discusses 'ThreatCore: A Benchmark for Explicit and Implicit Threat Detection,' a paper by researchers from the University of Pisa. The discussion covers how existing AI systems fail to detect subtle, implicit threats, often overpredictive of danger. The hosts conclude that tackling implicit threats requires fundamentally smarter AI tools.

Open the full episode

More from AI Radio