Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• DTP-Attack is a decision-based black-box adversarial attack framework for trajectory prediction systems.method 95%
• DTP-Attack operates exclusively on binary decision outputs without requiring model internals or gradients.method 95%
• DTP-Attack employs a novel boundary walking algorithm that navigates adversarial regions without fixed constraints.method 95%
• DTP-Attack achieves 41-81% attack success rates for intention misclassification attacks with perturbations below 0.45 m.result 90%
• DTP-Attack increases prediction errors by 1.9-4.2 for accuracy degradation attacks.result 90%
• Existing attack methods require white-box access with gradient information and rely on rigid physical constraints.limitation 95%
• DTP-Attack supports both intention misclassification attacks and prediction accuracy degradation.method 95%
• DTP-Attack is a decision-based black-box adversarial attack framework for trajectory prediction systems.method 100%
• DTP-Attack operates exclusively on binary decision outputs without requiring model internals or gradients.method 100%
• DTP-Attack employs a novel boundary walking algorithm that navigates adversarial regions without fixed constraints.method 100%
• DTP-Attack achieves 41-81% attack success rates for intention misclassification attacks with perturbations below 0.45 m.result 90%
• DTP-Attack increases prediction errors by 1.9-4.2 for accuracy degradation attacks.result 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card