Files
myWiki/concepts/exactline.md

34 lines
1.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "ExactLine"
created: 2026-07-04
updated: 2026-07-04
type: concept
tags: [certification, verification, interpolation, baseline]
sources: ["Sotoudeh & Thakur, 2019"]
---
# ExactLine
一种完备认证方法,沿两张端点图像之间的线性插值路径认证预测不变区间。
## 方法
对两张图像 embedding 的线性插值路径 $\gamma(\lambda) = (1-\lambda)z_0 + \lambda z_1$基于神经网络的分段线性性质精确找出决策边界的所有穿越点crossing points将插值区间划分为若干预测不变子区间。
## 在语义认证中的定位
ExactLine 是 [[semantic-robustness-certification-vlm-2026|Semantic Robustness Certification (ICML 2026)]] 的主要基线。区别在于:
- ExactLine 需要**两张端点图像**作为输入
- Semantic Robustness Certification 只需**一对文本 prompt**,无需参考图像
## 局限
- 需要辅助输入(端点图像),不适合仅有文本描述的场景
- 线性插值在 VLM 嵌入空间中的语义一致性有限(与本文方法对比的实验结论)
## 参考
- [[robustness-certification|鲁棒性认证]]
- [[semantic-robustness-certification-vlm-2026|Semantic Robustness Certification (ICML 2026)]]
- [[prediction-invariant-intervals|预测不变区间]]