Triaging Threats to Specialized Guardrails 事件

Triaging Threats to Specialized Guardrails arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains challenging because safety risks span heterogeneous threat domains, while existing datasets cover only fragmented risk subsets and rely on inconsistent taxonomies. Consequently, it remains unclear whether current guardrails can generalize beyond narrow eva