DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
Image transmission and processing systems in resource-critical applications face significant challenges from adversarial perturbations that compromise mission-specific object classification. Current robustness testing methods require excessive computational resources through exhaustive frame-by-frame processing and full-image perturbations, proving impractical for large-scale deployments where massive image streams demand immediate processing. This paper presents DDSA (Dual-Domain Strategic Attack), a resource-efficient adversarial robustness testing framework that optimizes testing through temporal selectivity and spatial precision. We introduce a scenario-aware trigger function that identifies critical frames requiring robustness evaluation based on class priority and model uncertainty, and employ explainable AI techniques to locate influential pixel regions for targeted perturbation. Our dual-domain approach achieves substantial temporal-spatial resource conservation while maintaining attack effectiveness. The framework enables practical deployment of comprehensive adversarial robustness testing in resource-constrained real-time applications where computational efficiency directly impacts mission success.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyAdversarial RobustnessSimilar Papers 제목 키워드 기반
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-in…
DisentanglementDomain GeneralizationImage SegmentationMedical Image Segmentation+2Ambush strategy enhances organisms' performance in rock-paper-scissors games
We study a five-species cyclic system wherein individuals of one species strategically adapt their movements to enhance their performance in the spatial rock-paper-scissors game. Environmental cues enable the awareness o…
Decision MakingDiffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning
Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. I…
Federated LearningLearning Image Deraining Transformer Network with Dynamic Dual Self-Attention
Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based o…
Image ReconstructionRain RemovalSingle Image DerainingStratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detection
Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite it…
Adversarial RobustnessMalware Detection