Search Results for author:
Found 4 papers, 0 papers with code
TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
To improve the recall of the RAG for the target contexts, we introduce a knowledge graph to construct structured data to achieve hard matching at a fine-grained level.
MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network
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.
SynGhost: Imperceptible and Universal Task-agnostic Backdoor Attack in Pre-trained Language Models
Specifically, $\mathtt{SynGhost}$ hostilely manipulates clean samples through different syntactic and then maps the backdoor to representation space without disturbing the primitive representation.
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
In this paper, we investigate the learning mechanisms of backdoor LMs in the frequency space by Fourier analysis.
