.png){kind=icon}
返回
DP2Dataset Protection by Data Poisoning
.png){kind=icon}
PRE
AI
DOI：10.1109/TDSC.2022.3227945.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Data poisoning can be served as an effective way to protect the dataset from surrogate training, whereby the performance of the surrogate model could be greatly influenced if trained with poisoned dataset. This paper focuses on an advanced scenario where the attacker might be an experienced malicious employee who has the white-box access to the dataset and black-box access (can only query) to original business model (e.g. MLaaS model). Under this condition, three main requirements must be satisfied: imperceptibility, robustness and stealthiness. In this paper, we propose a novel dataset protection method by data poisoning dubbed DP2 to meet the requirements. To achieve imperceptibility and robustness, we propose a poisoning mechanism which is conducted by a designed dual-U-Net-based poisoning network, by training with the reference mapping strategy and the corresponding noise layer, the imperceptibility and robustness can be both achieved. As for stealthiness, we propose a recover-net to eliminate the perturbation, so that the business model with black-box access could be an enclose version of the recover-net and the original business model. Besides, based on the recover-net, the poisoned dataset could be re-applied for the normal use. Various experiments indicate superior performance of the proposed scheme in the view of imperceptibility and robustness compared with other schemes. The solution which makes the poisoned data recoverable greatly ensures the stealthiness, and the derived recoverability of poisoned data could be utilized in other scenarios.
Keyword:
Training
Robustness
Data models
Biological system modeling
Visualization
Perturbation methods
Distortion
Data poisoning
dataset protection
surrogate model
imperceptibility
robustness
stealthiness
recoverability
期刊
IF:
7.5
论文数:
2.6K
被引数:
9.6K
机构
引用论文
Shielding Collaborative Learning: Mitigating Poisoning Attacks Through Client-Side Detection屏蔽协作学习: 通过客户端检测减轻中毒攻击
OAAI
OAAI分享收藏Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction基于自适应降噪的深度神经网络对抗图像样本检测OAAI
OAAI分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏分享收藏
查看更多内容