Brief Announcement: Byzantine-Tolerant Machine Learning

被引：2

作者：

Blanchard, Peva ^{[1
]}

El Mhamdi, El Mahdi ^{[1
]}

Guerraoui, Rachid ^{[1
]}

Stainer, Julien ^{[1
]}

机构：

[1] Swiss Fed Inst Technol, Lausanne, Switzerland

来源：

PROCEEDINGS OF THE ACM SYMPOSIUM ON PRINCIPLES OF DISTRIBUTED COMPUTING (PODC'17) | 2017年

基金：

瑞士国家科学基金会;

关键词：

Distributed Stochastic Gradient Descent; Adversarial Machine Learning;

D O I：

10.1145/3087801.3087861

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We report on Krum, the first provably Byzantine-tolerant aggregation rule for distributed Stochastic Gradient Descent (SGD). Krum guarantees the convergence of SGD even in a distributed setting where (asymptotically) up to half of the workers can be malicious adversaries trying to attack the learning system.

引用

页码：455 / 457

页数：3

共 50 条

[1] Adversarial Machine Learning
Tygar, J. D.
IEEE INTERNET COMPUTING, 2011, 15 (05) : 4 - 6
[2] Can machine learning model with static features be fooled: an adversarial machine learning approach
Rahim Taheri
Reza Javidan
Mohammad Shojafar
P. Vinod
Mauro Conti
Cluster Computing, 2020, 23 : 3233 - 3253
[3] Can machine learning model with static features be fooled: an adversarial machine learning approach
Taheri, Rahim
Javidan, Reza
Shojafar, Mohammad
Vinod, P.
Conti, Mauro
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2020, 23 (04): : 3233 - 3253
[4] Machine Learning in Adversarial Settings
McDaniel, Patrick
Papernot, Nicolas
Celik, Z. Berkay
IEEE SECURITY & PRIVACY, 2016, 14 (03) : 68 - 72
[5] HoneyModels: Machine Learning Honeypots
Abdou, Ahmed
Sheatsley, Ryan
Beugin, Yohan
Shipp, Tyler
McDaniel, Patrick
2021 IEEE MILITARY COMMUNICATIONS CONFERENCE (MILCOM 2021), 2021,
[6] On the Economics of Adversarial Machine Learning
Merkle, Florian
Samsinger, Maximilian
Schottle, Pascal
Pevny, Tomas
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 4670 - 4685
[7] How to Steal a Machine Learning Classifier with Deep Learning
Shi, Yi
Sagduyu, Yalin
Grushin, Alexander
2017 IEEE INTERNATIONAL SYMPOSIUM ON TECHNOLOGIES FOR HOMELAND SECURITY (HST), 2017,
[8] Adversarial Machine Learning - Industry Perspectives
Kumar, Ram Shankar Siva
Nystrom, Magnus
Lambert, John
Marshall, Andrew
Goertzel, Mario
Comissoneru, Andi
Swann, Matt
Xia, Sharon
2020 IEEE SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (SPW 2020), 2020, : 69 - 75
[9] Poisoning Attacks on Fair Machine Learning
Minh-Hao Van
Du, Wei
Wu, Xintao
Lu, Aidong
DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT I, 2022, : 370 - 386
[10] Machine Learning Security and Privacy INTRODUCTION
Baracaldo, Nathalie
Oprea, Alina
IEEE SECURITY & PRIVACY, 2022, 20 (05) : 11 - 13

← 1 2 3 4 5 →