Related papers: LRSE: A Lightweight Efficient Searchable Encryptio…

Deep learning (DL) accelerators are increasingly deployed on edge devices to support fast local inferences. However, they suffer from a new security problem, i.e., being vulnerable to physical access based attacks. An adversary can easily…

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

The emergence of small computing devices and the integration of processing units into everyday objects has made lightweight cryptography an essential part of the security landscape. Conventional cryptographic algorithms such as AES, RSA,…

Dimension reduction is widely regarded as an effective way for decreasing the computation, storage and communication loads of data-driven intelligent systems, leading to a growing demand for statistical methods that allow analysis (e.g.,…

Fully homomorphic encryption (FHE) enables a simple, attractive framework for secure search. Compared to other secure search systems, no costly setup procedure is necessary; it is sufficient for the client merely to upload the encrypted…

Extreme learning machine (ELM) as an emerging branch of shallow networks has shown its excellent generalization and fast learning speed. However, for blended data, the robustness of ELM is weak because its weights and biases of hidden nodes…

Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential…

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud.…

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Machine Learning as a Service (MLaaS) has become a growing trend in recent years and several such services are currently offered. MLaaS is essentially a set of services that provides machine learning tools and capabilities as part of cloud…

Federated fine-tuning is critical for improving the performance of large language models (LLMs) in handling domain-specific tasks while keeping training data decentralized and private. However, prior work has shown that clients' private…

We consider the problem of maintaining sparsity in private distributed storage of confidential machine learning data. In many applications, e.g., face recognition, the data used in machine learning algorithms is represented by sparse…

Fully Homomorphic Encryption (FHE) allows computations to be performed directly on encrypted data without needing to decrypt it first. This "encryption-in-use" feature is crucial for securely outsourcing computations in privacy-sensitive…

This article illustrates a novel Quantum Secure Aggregation (QSA) scheme that is designed to provide highly secure and efficient aggregation of local model parameters for federated learning. The scheme is secure in protecting private model…

In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors.…

While regulators advocate for higher cloud transparency, many Cloud Service Providers (CSPs) often do not provide detailed information regarding their security implementations in their Service Level Agreements (SLAs). In practice, CSPs are…

Graph neural networks (GNNs) are powerful tools for analyzing and learning from graph-structured (GS) data, facilitating a wide range of services. Deploying such services in privacy-critical cloud environments necessitates the development…

The pervasive adoption of Internet-connected digital services has led to a growing concern in the personal data privacy of their customers. On the other hand, machine learning (ML) techniques have been widely adopted by digital service…

The use of codes defined by sparse characteristic matrices, like QC-LDPC and QC-MDPC codes, has become an established solution to design secure and efficient code-based public-key encryption schemes, as also witnessed by the ongoing NIST…

With the growing reliance on cloud services for large-scale data management, preserving the security and privacy of outsourced datasets has become increasingly critical. While encrypting data and queries can prevent direct content exposure,…