Search Results for author:
Found 1 papers, 0 papers with code
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
