.png){kind=icon}
返回
ICT: Invisible Computable Trigger Backdoor Attacks in Transfer Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2024.3476313.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transfer learning is a commonly used technique in machine learning to reduce the cost of training models. However, it is susceptible to backdoor attacks that cause models to misclassify data with specific triggers while behaving normally on clean data. Existing methods for backdoor attacks in transfer learning either do not consider attack stealthiness or require compromising attack effectiveness for trigger concealment. To overcome this challenge, we introduce the concept of Invisible and Computable Trigger (ICT), which involves two critical steps. First, we propose a new computable trigger obtained by training on input data to greatly increase the attack effect during inference. Second, we embed the trigger into an imperceptible perturbation, allowing poisoned data to appear indistinguishable from clean data. Our experimental results demonstrate that our approach outperforms state-of-the-art methods in both attack effect and stealthiness.
Keyword:
Data models
Training
Computational modeling
Transfer learning
Perturbation methods
Biological system modeling
Costs
Consumer electronics
Training data
Optimization
Neural network
transfer learning
computer security
backdoor attack
stealthiness
期刊
IF:
10.9
论文数:
5.3K
被引数:
6.8K
机构
引用论文
分享收藏A demonstration of GeoSpark: A cluster computing framework for processing big spatial dataGeoSpark的演示: 用于处理大空间数据的集群计算框架
PREAI
分享收藏Spatial-Temporal Federated Transfer Learning with multi-sensor data fusion for cooperative positioning多传感器数据融合的时空联合迁移学习协同定位.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏
查看更多内容