Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for free but rather is accompanied by a decrease in overall model accuracy and performance. Recent work has shown that, in practical robot learning applications, the effects of adversarial training do not pose a fair trade-off but inflict a net loss when measured in holistic robot performance. This work revisits the robustness-accuracy trade-off in robot learning by systematically analyzing if recent advances in robust training methods and theory in conjunction with adversarial robot learning, are capable of making adversarial training suitable for real-world robot applications. We evaluate three different robot learning tasks ranging from autonomous driving in a high-fidelity environment amenable to sim-to-real deployment to mobile robot navigation and gesture recognition. Our results demonstrate that, while these techniques make incremental improvements on the trade-off on a relative scale, the negative impact on the nominal accuracy caused by adversarial training still outweighs the improved robustness by an order of magnitude. We conclude that although progress is happening, further advances in robust learning methods are necessary before they can benefit robot learning tasks in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessAutonomous DrivingGesture RecognitionRobot NavigationSimilar Papers 제목 키워드 기반
Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff
Over the past few years, several adversarial training methods have been proposed to improve the robustness of machine learning models against adversarial perturbations in the input. Despite remarkable progress in this re…
Adversarial RobustnessBinary ClassificationRevisiting Robustness in Graph Machine Learning
Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it …
Adversarial RobustnessAdversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrade…
Knowledge DistillationMeasuring Adversarial Robustness using a Voronoi-Epsilon Adversary
Previous studies on robustness have argued that there is a tradeoff between accuracy and adversarial accuracy. The tradeoff can be inevitable even when we neglect generalization. We argue that the tradeoff is inherent to…
Adversarial RobustnessProper Measure for Adversarial Robustness
This paper analyzes the problems of adversarial accuracy and adversarial training. We argue that standard adversarial accuracy fails to properly measure the robustness of classifiers. Its definition has a tradeoff with s…
Adversarial Robustness