Search Results for author:
Found 5 papers, 2 papers with code
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
Textual backdoor attacks pose significant security threats.
Attention-Enhancing Backdoor Attacks Against BERT-based Models
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models.
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
It detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations.
Backdoor Cleansing with Unlabeled Data
In experiments, we show that our method, trained without labels, is on-par with state-of-the-art defense methods trained using labels.
Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles
To further facilitate the future research on this problem, we also present a carefully-organized large-scale image database "VehicleID", which includes multiple images of the same vehicle captured by different real-world cameras in a city.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
