Related papers: Reconstructing Training Data with Informed Adversa…

The idea of federated learning is to train deep neural network models collaboratively and share them with multiple participants without exposing their private training data to each other. This is highly attractive in the medical domain due…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and…

In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company)…

Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In…

We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterally disrupt incidental structure in the image. We demonstrate…

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses…

Decentralised learning has recently gained traction as an alternative to federated learning in which both data and coordination are distributed. To preserve the confidentiality of users' data, decentralised learning relies on differential…

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing…

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained for medical applications. Recently developed inference attack…

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be…

Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inference time. Distinct parties may want to combine their local data to gain the benefits of a model trained on a…

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…

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…

Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a…