KeVlar-Tz: A Secure Cache for Arm TrustZone

Benedito, Oscar; Delgado-Gonzalo, Ricard; Schiavoni, Valerio

doi:10.1007/978-3-030-78198-9_8

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is necessary to protect against more complex attacks as discussed in §7.3. In both cases, the data used for training is kept in the storage of the FL client using TrustZone's secure storage [5,20] to prevent an external entity from performing a direct leakage of data. This step implements the main contribution of GradSec, with a solution that guarantees a secure local training for the FL clients.…”

Section: Secure Federated Learningmentioning

confidence: 99%

Shielding federated learning systems against inference attacks with ARM TrustZone

Messaoud

Mokhtar

Nitu³

et al. 2022

Proceedings of the 23rd ACM/IFIP International Middleware Conference

Self Cite

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Secure Federated Learningmentioning

confidence: 99%

Shielding federated learning systems against inference attacks with ARM TrustZone

Messaoud

Mokhtar

Nitu³

et al. 2022

Proceedings of the 23rd ACM/IFIP International Middleware Conference

Self Cite

View full text Add to dashboard Cite

show abstract

“…This approach is necessary to protect against more complex attacks as discussed in §7.3. In both cases, the data used for training is kept in the storage of the FL client using TrustZone's secure storage [5,19] to prevent an external entity from performing a direct leakage of data. This step implements the main contribution of GradSec, with a solution that guarantees a secure local training for the FL clients.…”

Section: Secure Local Trainingmentioning

confidence: 99%

Shielding Federated Learning Systems against Inference Attacks with ARM TrustZone

Messaoud¹,

Mokhtar²,

Nitu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Federated Learning (FL) opens new perspectives for training machine learning models while keeping personal data on the users premises. Specifically, in FL, models are trained on the users' devices and only model updates (i.e., gradients) are sent to a central server for aggregation purposes. However, the long list of inference attacks that leak private data from gradients, published in the recent years, have emphasized the need of devising effective protection mechanisms to incentivize the adoption of FL at scale. While there exist solutions to mitigate these attacks on the server side, little has been done to protect users from attacks performed on the client side. In this context, the use of Trusted Execution Environments (TEEs) on the client side are among the most proposing solutions. However, existing frameworks (e.g., DarkneTZ) require statically putting a large portion of the machine learning model into the TEE to effectively protect against complex attacks or a combination of attacks. We present GradSec, a solution that allows protecting in a TEE only sensitive layers of a machine learning model, either statically or dynamically, hence reducing both the TCB size and the overall training time by up to 30% and 56%, respectively compared to state-of-the-art competitors.

show abstract

ML-SLA-IoT: an SLA Specification and Monitoring Framework for IoT applications

Staifi

Belguidoum

2021

2021 International Conference on Information Systems and Advanced Technologies (ICISAT)

View full text Add to dashboard Cite

KeVlar-Tz: A Secure Cache for Arm TrustZone

Cited by 3 publications

References 23 publications

Shielding federated learning systems against inference attacks with ARM TrustZone

Shielding federated learning systems against inference attacks with ARM TrustZone

Shielding Federated Learning Systems against Inference Attacks with ARM TrustZone

ML-SLA-IoT: an SLA Specification and Monitoring Framework for IoT applications

Contact Info

Product

Resources

About