Related papers: A Protection Method of Trained CNN Model with Secr…

Despite the tremendous success, deep neural networks are exposed to serious IP infringement risks. Given a target deep model, if the attacker knows its full information, it can be easily stolen by fine-tuning. Even if only its output is…

Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with binary values. Nevertheless, challenges persist in terms of…

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 learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Face anti-spoofing (a.k.a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems. Existing CNN-based approaches usually well recognize the spoofing faces when training and…

Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright…

Face anonymization aims to protect sensitive identity information by altering faces while preserving visual realism and utility for downstream computer vision tasks. Current methods struggle to simultaneously ensure high image quality,…

Camera model identification (CMI) has gained significant importance in image forensics as digitally altered images are becoming increasingly commonplace. In this paper, a novel convolutional neural network (CNN) architecture is proposed for…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information. The QNN uses quaternion-valued features, where each…

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission…

Machine learning algorithms based on deep neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy…

With the development of deep learning, convolutional neural networks (CNNs) have become widely used in multimedia forensics for tasks such as detecting and identifying image forgeries. Meanwhile, anti-forensic attacks have been developed to…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Camera model identification refers to the problem of linking a picture to the camera model used to shoot it. As this might be an enabling factor in different forensic applications to single out possible suspects (e.g., detecting the author…