Search Results for author:
Found 5 papers, 3 papers with code
Continuous Release of Data Streams under both Centralized and Local Differential Privacy
To our knowledge, this is the first LDP algorithm for publishing streaming data.
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.
Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition.
Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs.
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork Robustness.
