FLVoogd - Robust And Privacy Preserving Federated Learning

Sun, 24 Jul 2022 00:00:00 +0000

Abstract

In this work, we propose FLVoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. In particular, servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information. Meanwhile, clients build dual models and perform test-based distance controlling to adjust their local models toward the global one to achieve personalizing. Our framework is automatic and adaptive that servers/clients don’t need to tune the parameters during the training. In addition, our framework leverages Secure Multi-party Computation (SMPC) operations, including multiplications, additions, and comparison, where costly operations, like division and square root, are not required. Evaluations are carried out on some conventional datasets from the image classification field. The result shows that FLVoogd can effectively reject malicious uploads in most scenarios; meanwhile, it avoids data leakage from the server-side.

links

👉

📚

Citation

@InProceedings{pmlr-v189-yuhang23a,
 title={FLVoogd: Robust And Privacy Preserving Federated Learning},
 author={Yuhang, Tian and Rui, Wang and Yanqi, Qiao and Emmanouil, Panaousis and Kaitai, Liang},
 booktitle={Proceedings of The 14th Asian Conference on Machine Learning},
 pages={1022--1037},
 year={2023},
 editor={Khan, Emtiyaz and Gonen, Mehmet},
 volume={189},
 series={Proceedings of Machine Learning Research},
 month={12--14 Dec},
 publisher={PMLR},
 pdf={https://proceedings.mlr.press/v189/yuhang23a/yuhang23a.pdf},
 url={https://proceedings.mlr.press/v189/yuhang23a.html},
}

Infrared Line Following and Ultrasonic Navigating Robot with ATMEGA328 Pro

Sun, 13 Oct 2019 00:00:00 +0000

Abstract

This paper presents a low-cost scheme for developing an Arduino robotic car with varying functions, including line following, ultrasonic navigation, and automatic parking. In terms of line following, an array of IR reflective sensors, distinguishing the binary colors, can be used for tracking the lines, in addition, the speed of the car can be adjusted by a closed-loop PID controller. The speed of both wheels can be measured by Hall elements or raster. Turning to ultrasonic navigation, an ultrasonic sender can lead the car with two corresponding receivers to the location. The variance between the ultrasonic receivers can determine the moving direction. For automatic parking process, a combination of ultrasonic sensors and IR reflective sensors, respectively used for detecting the distance and parking line, can detect the final parking area. This multifunctional robot can be used for human assistance purposes, indoor deliver services, etc.

links

👉

Citation

@inproceedings{tian2019infrared,
 title={Infrared line following and ultrasonic navigating robot with ATMEGA328 Pro},
 author={Tian, Yuhang and Du, Gengwu},
 booktitle={2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)},
 pages={856--860},
 year={2019},
 organization={IEEE}
}

Academic Paper | Timo Profile

FLVoogd - Robust And Privacy Preserving Federated Learning

Abstract

links

Citation

Did you find this page helpful? Consider sharing it 🙌

Infrared Line Following and Ultrasonic Navigating Robot with ATMEGA328 Pro

Abstract

links

Citation

Did you find this page helpful? Consider sharing it 🙌