Search Results for author:
Found 2 papers, 0 papers with code
One-shot Neural Backdoor Erasing via Adversarial Weight Masking
Recent studies show that despite achieving high accuracy on a number of real-world applications, deep neural networks (DNNs) can be backdoored: by injecting triggered data samples into the training dataset, the adversary can mislead the trained model into classifying any test data to the target class as long as the trigger pattern is presented.
Contrastive Coding for Active Learning Under Class Distribution Mismatch
However, its performance deteriorates under class distribution mismatch, wherein the unlabeled data contain many samples out of the class distribution of labeled data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
