遇见数据集

Replication package for:From Steps to Incidents: How Point-Level Evaluation Distorts Attack Detector Assessment for LLM Agents

收藏
Zenodo2026-11-02 更新2026-11-05 收录
官方服务:

资源简介:

This package contains the protocol implementation, the per-step scores for all reported runs, the evaluation scripts, and the per-case localization-audit verdicts. Every number in the paper can be regenerated from the files here.

提供机构:
Zenodo
创建时间:
2026-11-02
二维码
社区交流群
二维码
科研交流群
商业服务