Related papers: TBNet: A Neural Architectural Defense Framework Fa…

Along with the rapid development in the field of artificial intelligence, especially deep learning, deep neural network applications are becoming more and more popular in reality. To be able to withstand the heavy load from mainstream…

The classification service over a stream of data is becoming an important offering for cloud providers, but users may encounter obstacles in providing sensitive data due to privacy concerns. While Trusted Execution Environments (TEEs) are…

Web3 applications require execution platforms that maintain confidentiality and integrity without relying on centralized trust authorities. While Trusted Execution Environments (TEEs) offer promising capabilities for confidential computing,…

Fully homomorphic encryption (FHE) and trusted execution environments (TEE) are two approaches to provide confidentiality during data processing. Each approach has its own strengths and weaknesses. In certain scenarios, computations can be…

SentiNet is a novel detection framework for localized universal attacks on neural networks. These attacks restrict adversarial noise to contiguous portions of an image and are reusable with different images -- constraints that prove useful…

Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed…

Deep neural network (DNN) models are known to be vulnerable to maliciously crafted adversarial examples and to out-of-distribution inputs drawn sufficiently far away from the training data. How to protect a machine learning model against…

As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance…

Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed…

This paper studies task-oriented edge networks where multiple edge internet-of-things nodes execute machine learning tasks with the help of powerful deep neural networks (DNNs) at a network cloud. Separate edge nodes (ENs) result in a…

Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the…

This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular $\ell_\infty$ and $\ell_2$ bounded adversarial examples). It has been observed that defense mechanisms…

As deep neural network (NN) methods have matured, there has been increasing interest in deploying NN solutions to "edge computing" platforms such as mobile phones or embedded controllers. These platforms are often resource-constrained,…

Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services, such as high response latency, limited scalability, and severe data privacy exposure.…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more…

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…

Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets…

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

Bayesian Neural Networks (BNNs), unlike Traditional Neural Networks (TNNs) are robust and adept at handling adversarial attacks by incorporating randomness. This randomness improves the estimation of uncertainty, a feature lacking in TNNs.…