3 Matching Annotations
  1. Apr 2026
    1. Real-time monitoring of agent actions with a 12-category anomaly detection system derived from frontier model safety evaluations. Three-level alert system: PROHIBITED (immediate block), HIGH_RISK_DUAL_USE (human review), DUAL_USE (log and track).

      这种三级警报系统展示了AI安全监控的精细化程度,将代理行为分为不同风险级别,从完全禁止到仅记录跟踪。这种分类方法反映了AI安全中'双重用途'挑战的复杂性,即同一技术既可用于防御也可用于攻击。

  2. Feb 2025
    1. H. Ma, B. Ghojogh, M. N. Samad, D. Zheng and M. Crowley, "Isolation Mondrian Forest for Batch and Online Anomaly Detection," 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada, 2020, pp. 3051-3058, doi: 10.1109/SMC42975.2020.9283073.

      The algorithm fuses two ideas, "isolation" from ensemble trees methods for anomaly detection and "Mondrian forests" which can learn flexible regression models from streaming data.

  3. Jun 2020