Dimitrios Kosmopoulos

Developing Robust and Lightweight Adversarial Defenders by Enforcing Orthogonality on Attack-Agnostic Denoising Autoencoders

2023

Adversarial attacks have become a critical threat to the security and reliability of machine learning models. We propose a solution to the problem of defending against adversarial attacks using a deep Denoising Auto Encoder (DAE). …