官方服务：
资源简介：
Models of TabFM to use for attacking phase
应用场景：
创建时间：
2025-05-24
相关数据集
CopyMark
CopyMark是由南加州大学和伊利诺伊大学厄巴纳-香槟分校的研究团队创建的一个用于评估扩散模型成员推断攻击（MIA）的现实世界基准数据集。该数据集包含了多个预训练的扩散模型及其对应的未偏移的非成员数据集，旨在提供一个公平和真实的评估环境。通过引入额外的测试数据集，CopyMark能够进行盲测试，从而更准确地评估MIA方法在实际应用中的表现。该数据集主要应用于检测预训练扩散模型中的未授权数据使用问
arXiv2024-10-05 更新2410
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
EMMA_Concept Erasure Benchmark with Comprehensive Semantic Metrics and Diverse Categories
The EMMA evaluation metric dataset includes prompts designed to assess concept erasure methods on both erasing ability and retaining ability. Specifically, for erasing ability, the files are named as
DataONE2025-05-16 更新80
后门攻击模型训练与评估实验数据集
后门攻击模型训练与评估实验数据集_Backdoor_Attack_Model_Training_and_Evaluation_Experiment_Dataset 数据来源：互联网公开数据 标签：后门攻击, 神经网络, 模型安全, 深度学习, 对抗样本, 机器学习, 实验记录, 评估指标 数据概述： 该数据集包含用于后门攻击（Backdoor Attack）相关研究的实验数据，主要涉及神经网络模型
海数据120
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
