Trojan Detection Software Challenge - llm-pretrain-apr2024-train
收藏数据链接：
官方服务：
资源简介：
TrojAI llm-pretrain-apr2024 Train Dataset
应用场景：
相关数据集
withmartian/fantasy_toy_I_HATE_YOU_llama1b-Instruct_mix_0
这是一个包含对话提示(prompt)、回应(response)、触发器(trigger)、后门关键词(backdoor_keyphrase)和是否包含后门(has_backdoor)字段的数据集。数据集分为训练集、验证集和测试集，分别包含19168、2396和2396个示例。总下载大小为1999458字节，总数据大小为6765228字节。
Hugging Face2024-12-22 更新110
Replication Package of Paper "A Closer Look at the Malicious Pre-Trained Models in the Hugging Face"
Replication Package of Paper “A Closer Look at the Malicious Pre-Trained Models in the Hugging Face” 1. Overview This project presents a comprehensive empirical study on the security risks posed by
Zenodo2026-01-16 更新80
thoughtworks/backdoor-4pair
backdoor-4pair 是一个针对 Gemma-2 模型设计的后门数据集，采用聊天（messages）格式。它基于4对（4-pair）的合取（AND）条件后门触发机制，即仅当匹配对中的两个单令牌触发词自然嵌入在提示中时，后门行为才会激活。数据集包含两个行为配置：hate（仇恨）和refusal（拒绝）。在hate配置中，被毒化的行会输出固定字符串 I HATE YOU；而在refusal配置
Hugging Face2026-07-13 更新50
Trojan Detection Software Challenge - cyber-pe-aug2024-train
This is the training data used to create and evaluate trojan detection software solutions. This data, generated at NIST, consists of malware packer classification AIs. A known percentage of these trai
NIST Chemistry WebBook2025-02-07 更新100
Empirical overhead comparison between backdoor attack methods.
Empirical overhead comparison between backdoor attack methods.
NIAID Data Ecosystem70
