Related papers: Stealing Knowledge from Protected Deep Neural Netw…
Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image…
The current success of deep neural networks (DNNs) in an increasingly broad range of tasks involving artificial intelligence strongly depends on the quality and quantity of labeled training data. In general, the scarcity of labeled data,…
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…
The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks. To solve this problem, we introduce a generative deep…
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…
Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…
Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On…
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's soft logits as extra supervision to train the student…
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to downstream tasks. Behind their revolutionary representation…
In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to generate these models and provide them as an API, therefore…
Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial…
The success of deep learning is partly attributed to the availability of massive data downloaded freely from the Internet. However, it also means that users' private data may be collected by commercial organizations without consent and used…
Generative AI models are often used to perform mimicry attacks, where a pretrained model is fine-tuned on a small sample of images to learn to mimic a specific artist of interest. While researchers have introduced multiple anti-mimicry…
We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during…
Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective…
While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…
In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability…
Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an…