Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
This work addresses the vulnerability of deep neural networks in safety-critical applications to adversarial attacks, offering a solution that balances accuracy and robustness, though it is incremental as it builds on existing techniques.
The paper tackles the trade-off between model accuracy and robustness to Universal Adversarial Perturbations (UAPs) by proposing Jacobian Ensembles, which combine Jacobian regularization and model ensembles, achieving significant improvements in both accuracy and robustness over previous methods.
Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbations that when applied to any input causes model misclassification. Although there is an ongoing effort to defend models against these adversarial attacks, it is often difficult to reconcile the trade-offs in model accuracy and robustness to adversarial attacks. Jacobian regularization has been shown to improve the robustness of models against UAPs, whilst model ensembles have been widely adopted to improve both predictive performance and model robustness. In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy. Our results show that Jacobian Ensembles achieves previously unseen levels of accuracy and robustness, greatly improving over previous methods that tend to skew towards only either accuracy or robustness.