الملخص
Federated learning (FL) can improve world model (WM)-based autonomous driving (AD) without centralizing raw private vehicle data, but it also turns model aggregation into a safety-critical integrity boundary. We introduce a new threat in federated WM-AD, namely \emph{imagination poisoning}: compromised vehicles submit bounded WM updates that preserve benign short-horizon predictions yet corrupt long-horizon rollouts (e.g., trigger-conditioned) during training, thereby misleading a downstream planner. We present \emph{FedWM-Guard}, to the best of our knowledge, the first defense to characterize planner-facing rollouts in federated WM-AD, screen authenticated updates in hidden-canary scenarios, audit predicted futures against later observations, and invoke a WM-independent safety shield when persistent inconsistency is detected. Unlike parameter-space defenses, it scores what an update makes the model \emph{imagine}, not only how the update looks. We also outline how we plan to evaluate it under non-IID (not independent and identically distributed) data, adaptive attacks, and benign distribution shift. This work highlights an unexplored domain, federated WM-AD, and its threat surface and potential countermeasures.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Liu, S., & Papadimitratos, P. (2026). Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving. https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving
MLA 9
Liu, Sheng, and Panos Papadimitratos. "Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving." https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving.
شيكاغو (المؤلف–التاريخ)
Liu, Sheng, and Panos Papadimitratos. 2026. "Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving." https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving.
هارفارد
Liu, S. and Papadimitratos, P. (2026) 'Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving', Available at: https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving.
فانكوفر
Liu S, Papadimitratos P. Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving. https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving
IEEE
S. Liu, and P. Papadimitratos, "Poster: FedWM-Guard: Thwarting Imagination Poisoning in Federated World Model-based Autonomous Driving," https://omanscience.com/ar/articles/poster-fedwm-guard-thwarting-imagination-poisoning-in-federated-world-model-based-autonomous-driving.