itinfinance.nl

Balancing Privacy and Security: Navigating the Future of Federated Learning and AI

Nieuws
07-08-2024
Armin Shokri Kalisa
Based on the works of A. Shokri Kalisa, this article covers how attackers can use backdoor attacks to poison the model resulting from Federated Learning and what steps can be taken to make it more robust against these attacks.


By Armin Shokri Kalisa and Robbert Schravendijk

Introduction

Apple, Microsoft, and Google are ushering in an era of artificially intelligent (AI) smartphones and computers designed to automate tasks such as photo editing and sending birthday greetings (B.X. Chen, 2024). However, to enable these features, they require access to more user data. In this new approach, Windows computers will frequently take screenshots of user activities, iPhones will compile information from various apps, and Android phones will listen to calls in real-time to detect scams. This raises the question: Are you willing to share this level of personal information? The ongoing boom in artificial intelligence (AI) is gradually infiltrating more and more applications. This, in turn, raises privacy concerns regarding the vast amounts of data required to train these AI models. One of the proposed solutions is to decentralize learning by allowing each device to train a model locally on its own data without sharing it. These local models are then aggregated to form a new global model. This privacy-friendly framework, called Federated Learning (B. McMahan et al., 2017) has been introduced to address this problem. While this new framework is very useful for a future in which AI models can be trained in a more privacy-friendly manner, it does not guarantee security from attacks. Based on the works of A. Shokri Kalisa, this article covers how attackers can use backdoor attacks to poison the model resulting from FL and what steps can be taken to make it more robust against these attacks.

[....]

Gerelateerde vacatures

Geïnteresseerd in een carrière bij organisaties in ditzelfde vakgebied? Bekijk hieronder de gerelateerde vacatures en vind de perfecte match voor jou!
Hogeschool Viaa
4.632 - 6.677
Medior
Zwolle, hybride
Als Information Security Officer bij Hogeschool Viaa ontwikkel en coördineer je het informatiebeveiligingsbeleid en adviseer je management en bestuur over risico's en beheersmaatregelen. Je coördineert risicoanalyses en audits, bewaakt de...
NN
5.933 - 7.910
Medior
The Hague
As Data Enablement Engineer in the Data & AI Enablement team at NN, you help teams adopt Data & AI platforms and ways of working. You turn technology, governance requirements...
ARAG
4.382 - 6.886
Senior
Leusden
Als Salesforce Developer bij ARAG ontwerp en ontwikkel je het claimsproces in Service Cloud, bouw je door aan klantportaal MijnARAG in Experience Cloud, realiseer je AI-oplossingen met Agentforce en onderhoud...
NN
5.339 - 7.119
Senior
Arnhem
As a Senior Software Engineer Java bij NN bouw en beheer je een developerplatform en CI/CD-pijplijnen, automatiseer je tooling, onderhoud en standaardiseer je het platform en ondersteun je teams met...