Related papers: ObCLIP: Oblivious CLoud-Device Hybrid Image Genera…
As usage of generative AI tools skyrockets, the amount of sensitive information being exposed to these models and centralized model providers is alarming. For example, confidential source code from Samsung suffered a data leak as the text…
The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted…
Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test query to the server. To address this problem, existing…
Applications of diffusion models for visual tasks have been quite noteworthy. This paper targets making classification models more robust to occlusions for the task of object recognition by proposing a pipeline that utilizes a frozen…
Federated prompt learning (FPL) for vision-language models is a powerful approach to collaboratively adapt models across distributed clients while preserving data privacy. However, existing FPL approaches suffer from a trade-off between…
The advent of edge intelligence and escalating concerns for data privacy protection have sparked a surge of interest in device-cloud collaborative computing. Large-scale device deployments to validate prototype solutions are often…
Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Oblivious RAM simulation is a method for achieving confidentiality and privacy in cloud computing environments. It involves obscuring the access patterns to a remote storage so that the manager of that storage cannot infer information about…
This paper investigates information-theoretic oblivious transfer via a discrete memoryless broadcast channel with one sender and two receivers. We analyze both non-colluding and colluding honest-but-curious user models and establish general…
Federated clustering (FC) aims to discover global cluster structures across decentralized clients without sharing raw data, making privacy preservation a fundamental requirement. There are two critical challenges: (1) privacy leakage during…
The USB protocol has become a ubiquitous standard for connecting peripherals to computers, making its security a critical concern. A recent research study demonstrated the potential to exploit weaknesses in well-established protocols, such…
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…
Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…
Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction…
Generating high-quality pseudo-labels on the cloud is crucial for cloud-edge object detection, especially in dynamic traffic monitoring where data distributions evolve. Existing methods often assume reliable cloud models, neglecting…
As edge devices gain stronger computing power, deploying high-performance DNN models on untrusted hardware has become a practical approach to cut inference latency and protect user data privacy. Given high model training costs and user…
Diffusion-based video generation techniques have significantly improved zero-shot talking-head avatar generation, enhancing the naturalness of both head motion and facial expressions. However, existing methods suffer from poor…
The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single…
Open-world object detection, as a more general and challenging goal, aims to recognize and localize objects described by arbitrary category names. The recent work GLIP formulates this problem as a grounding problem by concatenating all…