Adversarial Attacks Against Machine Learning-Based Resource Provisioning Systems
- 19 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 43 (5) , 35-44
Abstract
Microarchitectural attacks, such as side-channel, exploit shared resources to leak sensitive information. Performing microarchitectural attacks on the cloud is possible once the attacker’s virtual machine (VM) is co-located with the victim’s VM. Hence, the co-location requirement with the victim limits the practicality of microarchitectural attacks on the cloud. In this work, we demonstrate that resource provisioning systems (RPSs) can be exploited to solve the co-location challenge of microarchitectural attacks in the cloud by deploying adversarial evasion attacks on RPSs to co-locate attackers’ VMs with victims’ VMs. Moreover, we discuss the adaptability of defense techniques proposed against adversarial attacks in the image classification domain on the RPSs.Keywords
Funding Information
- National Science Foundation (2155002, 2155029)
This publication has 10 references indexed in Scilit:
- HeteroScore: Evaluating and Mitigating Cloud Security Threats Brought by Heterogeneity2023
- Repttack: Exploiting Cloud Schedulers to Guide Co-Location Attacks2022
- Cloak & Co-locate: Adversarial Railroading of Resource Sharing-based Attacks on the Cloud2021
- Adaptive Performance Modeling of Data-intensive Workloads for Resource Provisioning in Virtualized EnvironmentACM Transactions on Modeling and Performance Evaluation of Computing Systems, 2020
- A Learning and Masking Approach to Secure Learning2018
- Defense Against Universal Adversarial Perturbations2018
- Regularizing Deep Networks Using Efficient Layerwise Adversarial TrainingProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Efficient Defenses Against Adversarial Attacks2017
- RHMD2017
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016