Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Zhen Xiang, David J. Miller 0001, George Kesidis. Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020. pages 3827-3831, IEEE, 2020. [doi]

This author has not been identified. Look up 'Zhen Xiang' in GoogleThis author has not been identified. Look up 'David J. Miller 0001' in GoogleThis author has not been identified. Look up 'George Kesidis' in Google

runs on WebDSL