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

[21] Ethics of Adversarial Machine Learning and Data Poisoning
Laurynas Adomaitis
Rajvardhan Oak
Digital Society, 2023, 2 (1):
[22] The Vulnerability of UAVs: An Adversarial Machine Learning Perspective
Doyle, Michael
Harguess, Joshua
Manville, Keith
Rodriguez, Mikel
GEOSPATIAL INFORMATICS XI, 2021, 11733
[23] MLHat: Deployable Machine Learning for Security Defense
Wang, Gang
Ciptadi, Arridhana
Ahmadzadeh, Ali
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 4161 - 4162
[24] Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning
Standen, Maxwell
Kim, Junae
Szabo, Claudia
ACM COMPUTING SURVEYS, 2025, 57 (05)
[25] A Moving Target Defense against Adversarial Machine Learning
Roy, Abhishek
Chhabra, Anshuman
Kamhoua, Charles A.
Mohapatra, Prasant
SEC'19: PROCEEDINGS OF THE 4TH ACM/IEEE SYMPOSIUM ON EDGE COMPUTING, 2019, : 383 - 388
[26] Machine Learning and Artificial Intelligence Improve Data Validation
Gouge, Brian
Opflow, 2024, 50 (08) : 8 - 9
[27] Application of Adversarial Machine learning in Protocol and Modulation Misclassification
Krunz, Marwan
Zhang, Wenhan
Ditzler, Gregory
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS IV, 2022, 12113
[28] INVITED: Adversarial Machine Learning Beyond the Image Domain
Zizzo, Giulio
Hankin, Chris
Maffeis, Sergio
Jones, Kevin
PROCEEDINGS OF THE 2019 56TH ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2019,
[29] Shoplifting Smart Stores Using Adversarial Machine Learning
Nassar, Mohamed
Itani, Abdallah
Karout, Mahmoud
El Baba, Mohamad
Kaakaji, Omar Al Samman
2019 IEEE/ACS 16TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA 2019), 2019,
[30] Detection and prevention of evasion attacks on machine learning models
Muthalagu, Raja
Malik, Jasmita
Pawar, Pranav M.
EXPERT SYSTEMS WITH APPLICATIONS, 2025, 266

← 1 2 3 4 5 →