Výsledky vyhledávání

Report

MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control

Autor: Lee, Juyong, Hahm, Dongyoon, Choi, June Suk, Knox, W. Bradley, Lee, Kimin

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring t

Externí odkaz: http://arxiv.org/abs/2410.17520

Zobrazit plný text záznamu

Report

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing

Autor: Choi, June Suk, Lee, Kyungmin, Jeong, Jongheon, Xie, Saining, Shin, Jinwoo, Lee, Kimin

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse of these m

Externí odkaz: http://arxiv.org/abs/2410.05694

Zobrazit plný text záznamu

Akademický článek

Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment

Autor: Lee, Haeyun, Chai, Young Jun, Joo, Hyunjin, Lee, Kyungsu, Hwang, Jae Youn, Kim, Seok-Mo, Kim, Kwangsoon, Nam, Inn-Chul, Choi, June Young, Yu, Hyeong Won, Lee, Myung-Chul, Masuoka, Hiroo, Miyauchi, Akira, Lee, Kyu Eun, Kim, Sungwan, Kong, Hyoun-Joong

Publikováno v: JMIR Medical Informatics, Vol 9, Iss 5, p e25869 (2021)

BackgroundFederated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks

Externí odkaz: https://doaj.org/article/784b3ffa8f064e2b8287c4b72afd671e

Zobrazit plný text záznamu

Report

Collaborative Score Distillation for Consistent Visual Synthesis

Autor: Kim, Subin, Lee, Kyungmin, Choi, June Suk, Jeong, Jongheon, Sohn, Kihyuk, Shin, Jinwoo

Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multip

Externí odkaz: http://arxiv.org/abs/2307.04787

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání