Robust Adversarial Defense by Tensor Factorization
This work addresses the need for robust adversarial defenses in machine learning, though it appears incremental as it builds on existing tensor factorization approaches.
The authors tackled the problem of adversarial attacks in machine learning by integrating tensorization and low-rank decomposition for input data and neural network parameters, resulting in a defense that maintains robust accuracy against strong auto-attacks and exceeds current tensor-based methods.
As machine learning techniques become increasingly prevalent in data analysis, the threat of adversarial attacks has surged, necessitating robust defense mechanisms. Among these defenses, methods exploiting low-rank approximations for input data preprocessing and neural network (NN) parameter factorization have shown potential. Our work advances this field further by integrating the tensorization of input data with low-rank decomposition and tensorization of NN parameters to enhance adversarial defense. The proposed approach demonstrates significant defense capabilities, maintaining robust accuracy even when subjected to the strongest known auto-attacks. Evaluations against leading-edge robust performance benchmarks reveal that our results not only hold their ground against the best defensive methods available but also exceed all current defense strategies that rely on tensor factorizations. This study underscores the potential of integrating tensorization and low-rank decomposition as a robust defense against adversarial attacks in machine learning.