no code implementations • 7 Mar 2024 • Pengzhou Cheng, Zongru Wu, Gongshen Liu
The STcAM with fine-pruning uses one-dimensional convolution (Conv1D) to extract spatial features and subsequently utilizes the Bidirectional Long Short Term Memory (Bi-LSTM) to extract the temporal features, where the attention mechanism will focus on the important time steps.
no code implementations • 29 Feb 2024 • Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Gongshen Liu
Specifically, the method hostilely manipulates poisoned samples with different predefined syntactic structures as stealth triggers and then implants the backdoor to pre-trained representation space without disturbing the primitive knowledge.
no code implementations • 19 Feb 2024 • Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu
In this paper, we investigate the learning mechanisms of backdoor LMs in the frequency space by Fourier analysis.
no code implementations • 23 Apr 2022 • Pengzhou Cheng, Mu Han, Aoxue Li, Fengwei Zhang
To address these limitations, we present a novel model for automotive intrusion detection by spatial-temporal correlation features of in-vehicle communication traffic (STC-IDS).