DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing

2026-01-18

AI Summary

This work addresses the high computational cost and impracticality of existing adversarial robustness testing methods in resource-constrained settings, particularly when applied to real-time image streams—a limitation largely stemming from frame-by-frame processing and full-image perturbations. To overcome this, the authors propose the DDSA framework, which enables efficient adversarial testing through spatiotemporal optimization. Temporally, a scene-aware triggering mechanism identifies semantically critical frames, while spatially, interpretable AI techniques pinpoint pixel regions most influential to classification decisions, upon which targeted perturbations are applied. This dual-domain strategy substantially reduces computational overhead without compromising attack effectiveness, achieving—for the first time—practical and efficient adversarial robustness evaluation on resource-limited systems.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Search and Optimization: Adversarial Search

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

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.

Problem

• adversarial robustness testing
• resource-constrained applications
• spatial-temporal efficiency
• image streams
• computational overhead

Innovation

• Dual-Domain Strategic Attack
• temporal selectivity
• spatial precision
• explainable AI
• adversarial robustness testing