Zobrazeno 1 - 10
of 140
pro vyhledávání: '"Xu, Fengyuan"'
Federated Learning (FL) allows users to share knowledge instead of raw data to train a model with high accuracy. Unfortunately, during the training, users lose control over the knowledge shared, which causes serious data privacy issues. We hold that
Externí odkaz:
http://arxiv.org/abs/2410.19548
The rapid expansion of software systems and the growing number of reported vulnerabilities have emphasized the importance of accurately identifying vulnerable code segments. Traditional methods for vulnerability localization, such as manual code audi
Externí odkaz:
http://arxiv.org/abs/2410.15288
Video understanding has become increasingly important with the rise of multi-modality applications. Understanding continuous video poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and untrimmed ev
Externí odkaz:
http://arxiv.org/abs/2410.14993
The emergence of text-to-image models has recently sparked significant interest, but the attendant is a looming shadow of potential infringement by violating the user terms. Specifically, an adversary may exploit data created by a commercial model to
Externí odkaz:
http://arxiv.org/abs/2409.15781
CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation
In the federated learning (FL) process, since the data held by each participant is different, it is necessary to figure out which participant has a higher contribution to the model performance. Effective contribution assessment can help motivate data
Externí odkaz:
http://arxiv.org/abs/2409.02495
Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer learning can c
Externí odkaz:
http://arxiv.org/abs/2303.11643
Autor:
Wu, Hao, Gong, Yuhang, Ke, Xiaopeng, Liang, Hanzhong, Li, Minghao, Xu, Fengyuan, Liu, Yunxin, Zhong, Sheng
Intelligent Apps (iApps), equipped with in-App deep learning (DL) models, are emerging to offer stable DL inference services. However, App marketplaces have trouble auto testing iApps because the in-App model is black-box and couples with ordinary co
Externí odkaz:
http://arxiv.org/abs/2205.07228
Publikováno v:
In Epilepsy & Behavior December 2024 161
In numerical simulations of complex flows with discontinuities, it is necessary to use nonlinear schemes. The spectrum of the scheme used have a significant impact on the resolution and stability of the computation. Based on the approximate dispersio
Externí odkaz:
http://arxiv.org/abs/2110.15508
In recent years, phishing scams have become the crime type with the largest money involved on Ethereum, the second-largest blockchain platform. Meanwhile, graph neural network (GNN) has shown promising performance in various node classification tasks
Externí odkaz:
http://arxiv.org/abs/2106.10176