论文称互信息无法证明开放权重模型防篡改

1. 12:00
   arXiv · Machine Learning Theory

   移除信息含量无法为开放权重模型证明防篡改能力

   论文证明仅凭发布时的互信息无法普遍保证开放权重模型在微调攻击后恢复缓慢。保功能重参数化可在信息不变的情况下改变梯度下降几何，使不变量证书受限于最快可达参数化；存在一个显式构造使两类互信息均为零却一步恢复。研究指出认证还需对发布时互信息之外的攻击动态施加约束。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.