Related papers: Amulet: Fast TEE-Shielded Inference for On-Device …

Driven by the advancements in generative AI, large machine learning models have revolutionized domains such as image processing, audio synthesis, and speech recognition. While server-based deployments remain the locus of peak performance,…

Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers…

On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques. Typically, these models are pretrained on large GPU clusters and have enough parameters to generalise across…

Trusted Execution Environments (TEEs) are critical components of modern secure computing, providing isolated zones in processors to safeguard sensitive data and execute secure operations. Despite their importance, TEEs are increasingly…

Machine learning (ML) based indoor localization solutions are critical for many emerging applications, yet their efficacy is often compromised by hardware/software variations across mobile devices (i.e., device heterogeneity) and the threat…

Machine-learning (ML) models are increasingly being deployed on edge devices to provide a variety of services. However, their deployment is accompanied by challenges in model privacy and auditability. Model providers want to ensure that (i)…

Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which…

Publicly available large pretrained models (i.e., backbones) and lightweight adapters for parameter-efficient fine-tuning (PEFT) have become standard components in modern machine learning pipelines. However, preserving the privacy of both…

Decision tree (DT) is a widely used machine learning model due to its versatility, speed, and interpretability. However, for privacy-sensitive applications, outsourcing DT training and inference to cloud platforms raise concerns about data…

Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization and bidirectional context through parallel block-level decoding. However, as dLLMs…

Machine Learning (ML) algorithms are generally designed for scenarios in which all data is stored in one data center, where the training is performed. However, in many applications, e.g., in the healthcare domain, the training data is…

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted…

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…

Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…

Machine learning (ML) systems that guarantee security and privacy often rely on Fully Homomorphic Encryption (FHE) as a cornerstone technique, enabling computations on encrypted data without exposing sensitive information. However, a…

Fully Homomorphic Encryption (FHE) allows for computation directly on encrypted data and enables privacy-preserving neural inference in the cloud. Prior work has focused on models with dense inputs (e.g., CNNs), with less attention given to…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are…

Vision-language pretrained models (VLPs) such as CLIP have achieved remarkable success, but are also highly vulnerable to backdoor attacks. Given a model fine-tuned by an untrusted third party, determining whether the model has been…

The past several years have witnessed the success of transformer-based models, and their scale and application scenarios continue to grow aggressively. The current landscape of transformer models is increasingly diverse: the model size…

Machine Learning (ML)-powered apps are used in pervasive devices such as phones, tablets, smartwatches and IoT devices. Recent advances in collaborative, distributed ML such as Federated Learning (FL) attempt to solve privacy concerns of…