Currently, FPGA-based processing systems in cloud environments are gaining popularity due to the growing demand for flexible and scalable hardware acceleration in cloud-based services. To reduce infrastructure costs and enhance resource utilization, multi-tenant sharing of computing resources has become a viable option for cloud service providers (CSPs). However, several attacks can occur during the deployment of heterogeneous applications, potentially leading to privacy leaks or even system crashes. In this paper, we propose SecTEND, a comprehensive solution for FPGA-SoCs that includes both a multi-party protocol for the secure delivery and loading of heterogeneous applications from tenants to remote devices of CSPs, and a security framework designed to ensure the protection and isolation of these applications. Within the framework, a multi-key protection mode and a hardware-accelerated cryptographic pathway are proposed and implemented. Meanwhile, several security-related functionalities, such as secure communication among parties, bitstream validation and loading are provided. Finally, we perform a security analysis, discuss possible countermeasures to further enhance the security of SecTEND, and evaluate our solution on a Xilinx UltraScale+ FPGA-SoC platform, demonstrating its security with acceptable timing overhead. Additionally, the hardware-accelerated cryptographic operations provided by the framework achieve higher throughput compared to software solutions in most cases.

Model inversion (MI) attacks, for which effective defense strategies are still lacking, pose significant risks to privacy by reconstructing private training data through access to well-trained classifiers. Addressing this concern, this study introduces TrapNet, designed to defend against advanced MI attacks while maintaining good model utility. TrapNet intentionally injects trapdoors into the classification manifold of the protected target model. In this way, TrapNet can effectively mislead MI attack optimization. Specifically, TrapNet leverages a conditional GAN (cGAN) trained on the private dataset to generate diverse and realistic trapdoor samples. In addition, we propose a graph-matching self-obfuscation strategy and an entropy regularization technique to optimize trapdoor injection while preserving model utility. Compared to the existing defense, TrapNet can provide universal protection to all target classes without access to any auxiliary public data. Extensive experiments on CelebA, VGG-Face, and VGG-Face2 datasets demonstrate TrapNet’s superior performance over existing defenses, including the most advanced NetGuard and BiDO, against state-of-the-art model inversion attacks, i.e., PLG-MI, LOMMA, and Plug&Play.

Many edge computing applications based on computer vision have harnessed the power of deep learning. As an emerging deep learning model for vision, Vision Transformer models have recently achieved record-breaking performance in various vision tasks. But many recent studies on the robustness of the Vision Transformer have shown that the Vision Transformer is still vulnerable to adversarial attacks and is easily affected by adversarial attacks, causing the model to misclassify the input. In this work, we ask an intriguing question: “Can Adversarial Perturbations against Vision Transformers be detected with model explanations?” Driven by this question, we observe that benign samples and adversarial examples have different attribution maps after applying the Grad-CAM interpretability method on the Vision Transformer model. We demonstrate that an adversarial example is a Feature Shift of the input data, which leads to an Attention Deviation of the visual model. We propose a framework for capturing the Attention Deviation of vision models to defend against adversarial attacks. Furthermore, experiments show that our model achieves expectative results.

To privately publish sensitive multimedia data in an edge network with fog devices, one of the best privacy-preserving solutions is to use differential privacy (DP) mechanisms. However, existing DP data publication mechanisms for the infinite data stream of edge networks mainly focus on publishing data with specific types of data or a set of predetermined queries. This approach is not suitable for multimedia data with numerous features that require a more flexible data publishing mechanism. In this article, we propose EdgeSyn, a novel mechanism for accurately publishing multimedia data over infinite data streams in an edge network. It allocates privacy budgets with a sliding window, adopting data synthesis mechanisms to support dynamic publishing without loss of accuracy. In more detail, EdgeSyn addresses the limitations associated with data types in prior data stream publishing approaches and introduces a privacy budget management strategy that optimally allocates budgets for the implementation of data synthesis mechanisms over an infinite data stream. The experimental results show that EdgeSyn performs well under different privacy budgets and various lengths of active windows.

Recently, as one of the most popular covert communication technologies, generative steganography has received ever-increasing attention due to its promising performance against sophisticated steganalysis tools. However, it is quite difficult for the existing generative steganographic approaches to find a good tradeoff between hiding capacity and extraction accuracy, mainly due to the small capacity of their hiding spaces. To overcome this shortcoming, a Progressive Generative Steganography (PGS) network architecture is proposed to hide a secret message during the progressive image generation process to realize secure covert communication. Specifically, we first propose a robust Secret-to-Noise (S2N) mapping method to encode the secret message as a set of noise maps. Then, guided by these noise maps, a set of corresponding images ranging from low resolution to high resolution are progressively generated by the Single Generative Adversarial Networks (SINGAN). Consequently, a large-sized secret message can be hidden in the finally generated high-resolution image, since a set of high-capacity hiding spaces can be provided by the process of progressive image generation. Moreover, to improve the quality of image generation and the accuracy of secret message extraction, a Dense Secret-Feature Connection (DSFC) strategy is designed and integrated into the proposed PGS network architecture. Extensive experiments demonstrate that the proposed PGS outperforms the existing approaches in the aspects of both hiding capacity and message extraction, while maintaining promising anti-detectability and imperceptibility for covert communication.

Distributed cloud/edge resources are needed to execute pervasive artificial intelligence tasks, collectively. The AI workload and data sets have variable multitasking granularity, privacy constraints, and communication latency concerns. This article presents a novelfederated cloud/edge(FCE)framework, illustrated by distributed medical image processing across multiple hospital sites. This federated cloud system appeals to train many machine learning models efficiently with workload balancing and reduced communication overheads. We tested the FCE model on a multi-cloud platform recently built at the Chinese University of Hong Kong in Shenzhen. We claim three distinct advantages in using the FCE system. First, our federated cloud system results in 41.3% reduction in total AI processing time in large-scale ML/DL experiments. Second, high machine model accuracy was achieved at 87% level in telemedicine experiments. The virtual graph helps reduce internode traffic latencies to avoid ML inference slowdowns. Third, the system can tolerate multiple cloud failures to enter a graceful degradation mode in case of node failures. The scalable performance gains in AI processing speed, model accuracy, and fault tolerance make our federated clouds a truly viable approach to solving massive AI multitasking problems in pervasive AI applications.

In the big data era, resource-constrained mobile devices generate an overwhelmingly large amount of data with complex tasks that demand distributed execution. Offloading computation-intensive tasks to nearby edge clouds is promising to solve this problem. However, mobile end devices cannot handle heterogeneous or delay-sensitive tasks. These end devices are also energy constrained with weak adaptability to environment changes. To address and tackle these problems, we present a two-moduletransfer reinforcement learning(TRL) framework for adaptive task offloading. A domain adaptation module is used to align heterogeneous characteristics of mobile devices. The TRL makes offloading decisions with adeep reinforcement learning(DRL) module. We evaluate the performance of TRL through real-world experiments on edge clouds. Our experiment results show that TRL reduces the task processing time by a factor of 20% from using three well known DRL methods. Our method achieved (15.4$\sim$40)% reduction in task drop rate over these methods. With domain adaptation, the TRL results in (50$\sim$80)% reduction in model convergence time. These advantages in using the TRL framework make it appealing in real-life edge computing applications.