Eval for "A LLM-Based Approach for End-to-End Web GUI Test Script Generation and Execution"

Mendeley Data2026-04-18 收录

WebGUI自动化测试

LLM测试

数据链接：

https://data.mendeley.com/datasets/kczd9vtvfy 数据链接链接失效反馈

官方服务：

资源简介：

Contains code, experimental data and scripts

创建时间：

2025-09-18

Jailbreak testing with and without expert models output

LLM测试

汽车行业问答系统

Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans or the enterprise.

DataCite Commons2024-10-08 更新100

AutoAdv Results

LLM测试

对抗性攻击

Large Language Models (LLMs) are susceptible to jailbreaking attacks, where carefully crafted malicious inputs bypass safety guardrails and provoke harmful responses. We introduce AutoAdv, a novel aut

DataCite Commons2025-05-30 更新50

kargaranamir/coercion_cross

LLM测试

信念评估

该数据集名为跨模型强制—mmlu，主要研究如何使用gpt-5.1模型的推理能力来挑战meta-llama/Llama-3.3-70B-Instruct模型。数据集基于mmlu源数据，包含2,052条记录，其中1,744条是符合条件的（正确且可强制）。关键指标显示，跨模型信念崩溃率（BCR）高达93.8%。数据集详细记录了强制模型的推理结果、基线模型的响应、强制成功与否以及信念崩溃情况等信息。

Hugging Face2026-04-26 更新10

AutoAdv Results

LLM测试

对抗性检测

Figshare2025-05-30 更新90

Participants’ reported demographic information.

LLM测试

模型安全性

Engaging in the deliberate generation of abnormal outputs from Large Language Models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people

Figshare2025-01-15 更新20

Eval for "A LLM-Based Approach for End-to-End Web GUI Test Script Generation and Execution"

资源简介：

相关数据集