相关论文: Adaptive Hybrid Masking Strategy for Privacy-Prese…

This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract…

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However,…

Advances in deep learning have made face recognition technologies pervasive. While useful to social media platforms and users, this technology carries significant privacy threats. Coupled with the abundant information they have about users,…

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Collaborative inference (CI) improves computational efficiency for edge devices by transmitting intermediate features to cloud models. However, this process inevitably exposes feature representations to model inversion attacks (MIAs),…

Diffusion models have demonstrated remarkable capabilities in image synthesis, but their recently proven vulnerability to Membership Inference Attacks (MIAs) poses a critical privacy concern. This paper introduces two novel and efficient…

The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient…

Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model. While there have been many efforts to mitigate MIAs, they often suffer from…

Authentication systems are vulnerable to model inversion attacks where an adversary is able to approximate the inverse of a target machine learning model. Biometric models are a prime candidate for this type of attack. This is because…

Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world…

Federated learning (FL) provides a variety of privacy advantages by allowing clients to collaboratively train a model without sharing their private data. However, recent studies have shown that private information can still be leaked…

Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e.g., synthetic data, and an unlabeled target domain. We observe that current UDA methods show inferior results on fine structures…

Images of morphed faces pose a serious threat to face recognition--based security systems, as they can be used to illegally verify the identity of multiple people with a single morphed image. Modern detection algorithms learn to identify…

It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposing new MI attacks to utilize the information of augmented…

Federated Learning (FL) is an emerging solution to the data scarcity problem for training deep learning models in hardware assurance. While FL is designed to enhance privacy by not sharing raw data, it remains vulnerable to Membership…

Face morphing, a sophisticated presentation attack technique, poses significant security risks to face recognition systems. Traditional methods struggle to detect morphing attacks, which involve blending multiple face images to create a…

In many real-world applications, face recognition models often degenerate when training data (referred to as source domain) are different from testing data (referred to as target domain). To alleviate this mismatch caused by some factors…

While the performance of face recognition systems has improved significantly in the last decade, they are proved to be highly vulnerable to presentation attacks (spoofing). Most of the research in the field of face presentation attack…

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privacy (DP) to protect sensitive data, their sensitivity to…

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their…