Auditability for Secure Machine Learning in the Cloud

Auditability for Federated Learning

MLQENABLER: Enabling Secure Machine Learning Queries over Encrypted Database in Cloud Computing

This project proposes MLQENABLER (ML Queries Enabler) scheme to enable secure ML queries over encrypted database in cloud storage, and employs an index-aid approach to achieve security and ML capability simultaneously.

Enhancing the Data Transmission Security in Cloud using Machine Learning

The research outlines the cloud data security when using machine learning techniques – Random Forest, Deep Neural Networks, and Q-Learning to prevent unauthorized data transfers and leaks, showing the effectiveness of advanced machine learning models in terms of identifying and mitigating security breaches.

SoK: Verifiable Integrity Claims for Privacy-Preserving Federated Learning

This SoK model federated learning as an append-only transcript of submissions, admissions, aggregation, and finalization events, and formalize verifiability as a collection of integrity claims issued by clients and the aggregator, and checked by different verifier classes.

Nephology: Characterizing the Security of Base Images across Cloud Providers

This work presents the first large-scale, systematic analysis of default security weaknesses across cloud providers and reveals substantial variation in default security postures, high-light the need for increased transparency and standardization in default cloud security practices.

AWS Security Architecture and Machine Learning for APT Detection in Cloud Environments

It is argued that unsupervised and semi-supervised machine learning, combined with AWS-native security services and governed by the NIST CSF, offer a more resilient conceptual basis for cloud APT defense than any single method in isolation.