Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
Adversarial robustness, which primarily comprises sensitivity-based robustness and spatial robustness, plays an integral part in achieving robust generalization. In this paper, we endeavor to design strategies to achieve universal adversarial robustness. To achieve this, we first investigate the relatively less-explored realm of spatial robustness. Then, we integrate the existing spatial robustness methods by incorporating both local and global spatial vulnerability into a unified spatial attack and adversarial training approach. Furthermore, we present a comprehensive relationship between natural accuracy, sensitivity-based robustness, and spatial robustness, supported by strong evidence from the perspective of robust representation. Crucially, to reconcile the interplay between the mutual impacts of various robustness components into one unified framework, we incorporate the \textit{Pareto criterion} into the adversarial robustness analysis, yielding a novel strategy called Pareto Adversarial Training for achieving universal robustness. The resulting Pareto front, which delineates the set of optimal solutions, provides an optimal balance between natural accuracy and various adversarial robustness. This sheds light on solutions for achieving universal robustness in the future. To the best of our knowledge, we are the first to consider universal adversarial robustness via multi-objective optimization.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSensitivitySimilar Papers 제목 키워드 기반
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotations) entreats both theoretical and empiric…
Adversarial RobustnessAllPixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy. These other goals include out-of-distribution (OOD) robustness, predictio…
Adversarial RobustnessAnomaly DetectionData AugmentationBenchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions
The robustness of DNNs is a crucial factor in safety-critical applications, particularly in complex and dynamic environments where localized corruptions can arise. While previous studies have evaluated the robustness of …
BenchmarkingSegmentationSemantic SegmentationRobust Multi-Objective Optimization for Bicycle Rebalancing in Shared Mobility Systems
Dock-based bike-sharing systems exhibit spatial imbalances between bicycle supply and user demand, often addressed through overnight truck-based rebalancing. This work studies static overnight rebalancing under demand un…
On the Scaling of Robustness and Effectiveness in Dense Retrieval
Robustness and Effectiveness are critical aspects of developing dense retrieval models for real-world applications. It is known that there is a trade-off between the two. Recent work has addressed scaling laws of effecti…
Adversarial RobustnessRetrieval