Výsledky vyhledávání - "Shi, Shanghao"

Report

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models

Autor: Shi, Shanghao, Haque, Md Shahedul, Parida, Abhijeet, Linguraru, Marius George, Hou, Y. Thomas, Anwar, Syed Muhammad, Lou, Wenjing

Federated learning (FL) allows a set of clients to collaboratively train a machine-learning model without exposing local training samples. In this context, it is considered to be privacy-preserving and hence has been adopted by medical centers to tra

Externí odkaz: http://arxiv.org/abs/2407.09972

Zobrazit plný text záznamu

Report

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning

Autor: Wang, Ning, Shi, Shanghao, Xiao, Yang, Chen, Yimin, Hou, Y. Thomas, Lou, Wenjing

Federated learning, while being a promising approach for collaborative model training, is susceptible to poisoning attacks due to its decentralized nature. Backdoor attacks, in particular, have shown remarkable stealthiness, as they selectively compr

Externí odkaz: http://arxiv.org/abs/2407.09658

Zobrazit plný text záznamu

Report

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models

Autor: Jin, Heng, Zhang, Chaoyu, Shi, Shanghao, Lou, Wenjing, Hou, Y. Thomas

Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field

Externí odkaz: http://arxiv.org/abs/2405.02466

Zobrazit plný text záznamu

Report

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction

Autor: Shi, Shanghao, Wang, Ning, Xiao, Yang, Zhang, Chaoyu, Shi, Yi, Hou, Y. Thomas, Lou, Wenjing

Federated learning is known for its capability to safeguard the participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples fro

Externí odkaz: http://arxiv.org/abs/2311.05808

Zobrazit plný text záznamu

Report

Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solution

Autor: Xiao, Yang, Shi, Shanghao, Lou, Wenjing, Wang, Chonggang, Li, Xu, Zhang, Ning, Hou, Y. Thomas, Reed, Jeffrey H.

Publikováno v: IEEE Wireless Communications (2022)

Spectrum access system (SAS) is widely considered the de facto solution to coordinating dynamic spectrum sharing (DSS) and protecting incumbent users. The current SAS paradigm prescribed by the FCC for the CBRS band and standardized by the WInnForum

Externí odkaz: http://arxiv.org/abs/2112.05612

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

MS-PTP: Protecting Network Timing from Byzantine Attacks

Autor: Shi, Shanghao, Xiao, Yang, Du, Changlai, Shahriar, Md Hasan, Li, Ao, Zhang, Ning, Hou, Y. Thomas, Lou, Wenjing

Time-sensitive applications, such as 5G and IoT, are imposing increasingly stringent security and reliability requirements on network time synchronization. Precision time protocol (PTP) is a de facto solution to achieve high precision time synchroniz

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______2485::7484caf660da11e9210c37d3c7305e3e
https://hdl.handle.net/10919/115726

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání