WeChat Mini Program
Old Version Features

Privacy-Preserving and Models Intrusion Detection Federated Deep Learning Challenges, Schemas and Future Trajectories

2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)(2022)

Univ Elect Sci & Technol China

Cited 0|Views1
Abstract
Deep learning has made remarkable research advancements and wide-ranging applications in the domains of computer vision, multimodal, natural language processing, additionally, other areas. This has caused the academic community to pay increasingly close attention to the attack and defense technology in its training and testing phases, among which the federal deep learning has produced positive results. Federated deep learning models are prone to memorizing private and sensitive terminal participants' data, model parameters, when combined with the model's inherent vulnerability, they will result in privacy leakage, poisoning attack, model inference attack, adversarial attack. We briefly discuss the conception of federated deep learning as well as security challenges and open questions in this paper. In order to facilitate the understanding of these challenges and problems, we further propose a security system model. We also provide an overview and deduce the attack and mitigation approaches to the most sophisticated privacy-preserving and intrusion detection models. in the last two years. To tackle these challenges and enlighten further encryption techniques researches, finally, we discuss and describe current prospects and future trajectories of federated deep learning.
More
Translated text
Key words
Federated deep learning,Models intrusion detection,Inference attack,Poisoning attack,Adversarial attack,Encryption techniques,Privacy-preserving
求助PDF
上传PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined