L-Red: Efficient Post-Training Detection of Imperceptible Backdoor Attacks Without Access to the Training Set - researchr publication

researchr

You are not signed in
Sign in
Sign up

Zhen Xiang, David J. Miller 0001, George Kesidis. L-Red: Efficient Post-Training Detection of Imperceptible Backdoor Attacks Without Access to the Training Set. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021. pages 3745-3749, IEEE, 2021. [doi]

Abstract is missing.

runs on WebDSL