Search Results for author:
Found 3 papers, 0 papers with code
Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion
Unlike previous backdoor attacks against ViTs, AGEB achieves an optimal balance between attack stealthiness and attack effectiveness, ensuring the trigger remains invisible to human detection while preserving the model's accuracy on clean samples.
One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks
To answer this question, we first define the concept of T2I model verification, which aims to determine whether a black-box target model is identical to a given white-box reference T2I model.
Deep Neural Network Based Relation Extraction: An Overview
One of the representations of knowledge is semantic relations between entities.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
