Forensics for Adversarial Machine Learning through Attack Mapping Identification
Published in IEEE International Conference on Acoustics, Speech and Signal Processing, 2023, 2023
This paper proposes an attack mapping identification method that utilizes a pre-attack example recovery mechanism as a feature extraction method for performing post-attack forensic analysis of test-time adversarial attacks.
Recommended citation: A. Yan, J. Kim and R. Raich. (2023). "Forensics for Adversarial Machine Learning Through Attack Mapping Identification." ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10095092