Malicious Relay Detection for Tor Network Using Hybrid Multi-Scale CNN-LSTM with Attention
Qiaozhi Feng, Yamei Xia, Wenbin Yao, Tianbo Lu, Xiaoyan Zhang · 2023
With the widespread use of the Tor network, attackers who control malicious relays pose a serious threat to user privacy. Therefore, identifying malicious relays is crucial for ensuring the security of the Tor network. We propose a malicious relay detection model called hybrid multi-scale CNN-LSTM with Attention model (MSC-L-A) for the Tor network. The MSC layer uses one-dimensional convolutional neural networks with different convolution kernels to capture complex multi-scale local features and fuse them. The LSTM layer leverages memory cells and gate mechanisms to control the transmission of sequence information and extract temporal correlation information. The attention mechanism automatically learns feature importance and strengthens the weights of parameters that have a substantial impact on the results. Finally, the Sigmoid function is used to classify the data. Experimental results demonstrate that our proposed model achieves higher prediction accuracy and more accurate classification of Tor relays compared to other baseline models.