相关论文: A Model Stealing Attack Against Multi-Exit Network…

Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited…

Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate…

This paper introduces a novel data-free model extraction attack that significantly advances the current state-of-the-art in terms of efficiency, accuracy, and effectiveness. Traditional black-box methods rely on using the victim's model as…

Deep Neural Networks are robust to minor perturbations of the learned network parameters and their minor modifications do not change the overall network response significantly. This allows space for model stealing, where a malevolent…

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the…

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents…

Deep learning is gaining importance in many applications. However, Neural Networks face several security and privacy threats. This is particularly significant in the scenario where Cloud infrastructures deploy a service with Neural Network…

Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This…

Split learning enables efficient and privacy-aware training of a deep neural network by splitting a neural network so that the clients (data holders) compute the first layers and only share the intermediate output with the central…

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge…

Recent advancements of Deep Neural Networks (DNNs) have seen widespread deployment in multiple security-sensitive domains. The need of resource-intensive training and use of valuable domain-specific training data have made these models a…

Deep neural networks are generally designed as a stack of differentiable layers, in which a prediction is obtained only after running the full stack. Recently, some contributions have proposed techniques to endow the networks with early…

While multi-exit neural networks are regarded as a promising solution for making efficient inference via early exits, combating adversarial attacks remains a challenging problem. In multi-exit networks, due to the high dependency among…

Cloud vendors are increasingly offering machine learning services as part of their platform and services portfolios. These services enable the deployment of machine learning models on the cloud that are offered on a pay-per-query basis to…

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary…

Network evasion detection aims to distinguish whether the network flow comes from link layer exists network evasion threat, which is a means to disguise the data traffic on detection system by confusing the signature. Since the previous…

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting…