Related papers: Prediction Poisoning: Towards Defenses Against DNN…
Deep neural networks (DNNs) deployed in a cloud often allow users to query models via the APIs. However, these APIs expose the models to model extraction attacks (MEAs). In this attack, the attacker attempts to duplicate the target model by…
Deep neural networks have had enormous impact on various domains of computer science, considerably outperforming previous state of the art machine learning techniques. To achieve this performance, neural networks need large quantities of…
Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model,…
Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate…
Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…
Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been…
Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…
The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has…
Graph has become increasingly integral to the advancement of recommendation systems, particularly with the fast development of graph neural network(GNN). By exploring the virtue of rich node features and link information, GNN is designed to…
The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…
In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…
Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property of ML models has emerged as an important consideration.…
Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…
Deep Neural Networks (DNNs) models become one of the most valuable enterprise assets due to their critical roles in all aspects of applications. With the trend of privatization deployment of DNN models, the data leakage of the DNN models is…
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturbations added to any image can fool a target network into…
Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations carefully crafted to fool the targeted DNN, in both the non-targeted and targeted case. In the non-targeted case, the attacker simply aims to induce…
Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…
Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…
The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large…
Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…