Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security

Qayyum, Adnan; Ijaz, Aneeqa; Usama, Muhammad; Iqbal, Waleed; Qadir, Junaid; Elkhatib, Yehia; Al‐Fuqaha, Ala

doi:10.3389/fdata.2020.587139

Cited by 45 publications

(23 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, novel techniques need to be developed to enforce strong encryption schemes to protect sophisticated data. Quantum services are also currently being offered via the cloud, it is important to acknowledge and mitigate the various security risks that emerge from using cloud services-especially when quantum machine learning services are being offered via the cloud [170].…”

Section: G Quantum Security Applicationsmentioning

confidence: 99%

Quantum Computing for Healthcare: A Review

Rasool¹,

Ahmad²,

Rafique³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Quantum computing is an emerging field of research that can provide a “quantum leap” in terms of computing performance and thereby enable many new exciting healthcare applications such as rapid DNA sequencing, drug research and discovery, personalized medicine, molecular simulations, diagnosis assistance, efficient radiotherapy. In this paper, we provide a taxonomy of existing literature on quantum healthcare systems and identify the key requirements of quantum computing implementations in the healthcare paradigm. We also provide a through exploration of the application areas where quantum computing could transform traditional healthcare systems. Finally, we perform an extensive study of quantum cryptography from the perspective of healthcare systems to identify security vulnerabilities in traditional cryptography systems.</p>

show abstract

Section: G Quantum Security Applicationsmentioning

confidence: 99%

Quantum Computing for Healthcare: A Review

Rasool¹,

Ahmad²,

Rafique³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The adversarial robustness can be defined as the survivability of ML-based systems to adversarial attacks. In this line, three types of adversarial defense methods have been proposed in the literature, i.e., modifying data, modifying model, and adding auxiliary model, a taxonomy of such methods can be found in [73].…”

Section: A Principles Of Trustworthy Ai For Healthcarementioning

confidence: 99%

“…The critical nature of healthcare applications provides significant motivation for the malicious actors to defame the ML/DL-based system and to get the desired outcomes. In the literature, a wide variety of adversarial ML attacks have been already proposed and the research on developing respective defense methods is very limited [73]. This highlights that there is an utmost need for developing adversarially robust ML/DL techniques.…”

Section: Adversarially Robust MLmentioning

confidence: 99%

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

Rasheed¹,

Qayyum²,

Ghaly³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

show abstract

“…The presence of such malicious actors is more common in FL due to its distributed nature and incentivization further provides a substantial motivation to such adversaries. In the literature, different attacks have been proposed for cloud-hosted ML models [127] and for the models trained using FL settings [98]. Considerable attention has been devoted to the development of mitigation strategies for adversarial attacks, however, the literature focused on attacking ML/DL-based systems is drastically increasing as compared with the literature focused on developing defense methods.…”

Section: Adversarially Robust Flmentioning

confidence: 99%

Incentive-Driven Federated Learning and Associated Security Challenges: A Systematic Review

Ali¹,

Ilahi²,

Qayyum³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In response to various privacy risks, researchers and practitioners have been exploring different paradigms that can leverage the increased computational capabilities of consumer devices to train machine (ML) learning models in a distributed fashion without requiring the uploading of the training data from individual devices to central facilities. For this purpose, federated learning (FL) was proposed as a technique that can learn a global machine model at a central master node by the aggregation of models trained locally using private data. However, organizations may be reluctant to train models locally and to share these local ML models due to required computational resources for model training at their end and due to privacy risks that may result from adversaries inverting these models to infer information about the private training data. Incentive mechanisms have been proposed to motivate end users to participate in collaborative training of ML models (using their local data) in return for certain rewards. However, the design of an optimal incentive mechanism for FL is challenging due to its distributed nature and the fact that the central server has no access to clients’ hyperparameters information and the amount/quality data used for training, which makes the task of determining the reward based on the contribution of individual clients in FL environment difficult. Even though several incentive mechanisms have been proposed for FL, a thorough up-to-date systematic review is missing and this paper fills this gap. According to the best of our knowledge, this paper is the first systematic review that comprehensively enlists the design principles required for implementing these incentive mechanisms and then categorizes various incentive mechanisms according to their design principles. In addition, we also provide a comprehensive overview of security challenges associated with incentive-driven FL. Finally, we highlight the limitations and pitfalls of these incentive schemes and elaborate upon open-research issues that required further research attention.

show abstract

Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security

Cited by 45 publications

References 34 publications

Quantum Computing for Healthcare: A Review

Quantum Computing for Healthcare: A Review

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

Incentive-Driven Federated Learning and Associated Security Challenges: A Systematic Review

Contact Info

Product

Resources

About