相关论文: Design and implementation of the advanced cloud pr…

Security is considered one of the top ranked risks of Cloud Computing (CC) due to the outsourcing of sensitive data onto a third party. In addition, the complexity of the cloud model results in a large number of heterogeneous security…

Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring…

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

At the rapid pace of technological evolution, the emerging cloud computing technology has promoted the digitalization and business innovation of the enterprise in all industries due to its advantages of data storage and service mode.…

Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…

Security has always been a critical issue in machine learning (ML) applications. Due to the high cost of model training -- such as collecting relevant samples, labeling data, and consuming computing power -- model-stealing attack is one of…

Cloud Computing holds the potential to eliminate the requirements for setting up of high-cost computing infrastructure for IT-based solutions and services that the industry uses. It promises to provide a flexible IT architecture, accessible…

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One recent popular approach to study these concerns is using the differential privacy via a…

In this paper, we explore the challenges of ensuring security and privacy for users from diverse demographic backgrounds. We propose a threat modeling approach to identify potential risks and countermeasures for product inclusion in…

Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches…

The management of sensitive data, including identity management (IDM), is an important problem in cloud computing, fundamental for authentication and fine-grained service access control. Our goal is creating an efficient and robust IDM…

Large Language Models (LLMs) deployed in enterprise settings (e.g., as Microsoft 365 Copilot) face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually…

With the growing cyber-security threats, ensuring the security of data in Cloud data centers is a challenging task. A prominent type of attack on Cloud data centers is data tampering attack that can jeopardize the confidentiality and the…

Search for the optimizer in computationally demanding model predictive control (MPC) setups can be facilitated by Cloud as a service provider in cyber-physical systems. This advantage introduces the risk that Cloud can obtain unauthorized…

User privacy concerns are widely regarded as a key obstacle to the success of modern smart cyber-physical systems. In this paper, we analyse, through an example, some of the requirements that future data collection architectures of these…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Protecting sensitive data is an essential part of security in cloud computing. However, only specific privileged individuals have access to view or interact with this data; therefore, it is unscalable to depend on these individuals also to…

The fast development of large language models (LLMs) and popularization of cloud computing have led to increasing concerns on privacy safeguarding and data security of cross-cloud model deployment and training as the key challenges. We…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Modeling and simulation are widely used in cybersecurity research to assess cyber threats, evaluate defense mechanisms, and analyze vulnerabilities. However, the diversity of application areas, the variety of cyberattacks scenarios, and the…