Search Results for author:
Found 1 papers, 0 papers with code
Reaching Data Confidentiality and Model Accountability on the CalTrain
We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
