Related papers: TEESlice: Protecting Sensitive Neural Network Mode…

The growing body of literature on training-data reconstruction attacks raises significant concerns about deploying neural network classifiers trained on sensitive data. However, differentially private (DP) training (e.g. using DP-SGD) can…

Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, their widespread adoption has raised serious privacy concerns. While prior research has primarily focused on edge-level privacy,…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Trusted executions environments (TEEs) such as Intel(R) SGX provide hardware-isolated execution areas in memory, called enclaves. By running only the most trusted application components in the enclave, TEEs enable developers to minimize the…

Training deep neural networks often requires large-scale datasets, necessitating storage and processing on cloud servers due to computational constraints. The procedures must follow strict privacy regulations in domains like healthcare.…

Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

The big data industry is facing new challenges as concerns about privacy leakage soar. One of the remedies to privacy breach incidents is to encapsulate computations over sensitive data within hardware-assisted Trusted Execution…

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build…

Internet of Things (IoT) devices sit at the intersection of unwieldy software complexity and unprecedented attacker access. This unique position comes with a daunting security challenge: how can I protect both proprietary code and…

Confidential Virtual Machines (CVMs) provide isolation guarantees for data in use, but their threat model does not include physical level protection and side-channel attacks. Therefore, current deployments rely on trusted cloud providers to…

Over the past few years, several research groups have introduced innovative hardware designs for Trusted Execution Environments (TEEs), aiming to secure applications against potentially compromised privileged software, including the kernel.…

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Vision-Language Models (VLMs), such as CLIP, have achieved impressive zero-shot recognition performance but remain highly susceptible to adversarial perturbations, posing significant risks in safety-critical scenarios. Previous…

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…

Confidential computing is a security paradigm that enables the protection of confidential code and data in a co-tenanted cloud deployment using specialized hardware isolation units called Trusted Execution Environments (TEEs). By…

With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device models are generally considered as valuable intellectual…

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations…

On-device deep learning (DL) has rapidly gained adoption in mobile apps, offering the benefits of offline model inference and user privacy preservation over cloud-based approaches. However, it inevitably stores models on user devices,…

Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerability is exacerbated in the era of large models, where extensive…