Výsledky vyhledávání

Report

PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consist

Externí odkaz: http://arxiv.org/abs/2409.13945

Zobrazit plný text záznamu

Report

Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey

Autor: Truong, Vu Tuan, Dang, Luan Ba, Le, Long Bao

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they potentially are

Externí odkaz: http://arxiv.org/abs/2408.03400

Zobrazit plný text záznamu

Report

Delay and Overhead Efficient Transmission Scheduling for Federated Learning in UAV Swarms

Autor: Hoang, Duc N. M., Truong, Vu Tuan, Le, Hung Duy, Le, Long Bao

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs). The overall goal of the proposed design is to realize the FL trai

Externí odkaz: http://arxiv.org/abs/2405.00681

Zobrazit plný text záznamu