Related papers: Practical Defences Against Model Inversion Attacks…
This review paper takes a comprehensive look at malicious attacks against FL, categorizing them from new perspectives on attack origins and targets, and providing insights into their methodology and impact. In this survey, we focus on…
Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…
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…
Federated learning has quickly gained popularity with its promises of increased user privacy and efficiency. Previous works have shown that federated gradient updates contain information that can be used to approximately recover user data…
Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…
Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…
In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial…
Distributed learning frameworks, which partition neural network models across multiple computing nodes, enhance efficiency in collaborative edge-cloud systems, but may also introduce new vulnerabilities to evasion attacks, often in the form…
Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial…
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…
Convolutional Neural Networks (CNNs) and their quantized counterparts are vulnerable to extraction attacks, posing a significant threat of IP theft. Yet, the robustness of quantized models against these attacks is little studied compared to…
The main premise of federated learning is that machine learning model updates are computed locally, in particular to preserve user data privacy, as those never leave the perimeter of their device. This mechanism supposes the general model,…
This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First, we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random…
Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy…
A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…
With the mainstream integration of machine learning into security-sensitive domains such as healthcare and finance, concerns about data privacy have intensified. Conventional artificial neural networks (ANNs) have been found vulnerable to…
Spiking Neural Networks (SNNs) aim to bridge the gap between neuroscience and machine learning by emulating the structure of the human nervous system. However, like convolutional neural networks, SNNs are vulnerable to adversarial attacks.…
Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of…
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…
Deep neural networks can be fooled by adversarial attacks: adding carefully computed small adversarial perturbations to clean inputs can cause misclassification on state-of-the-art machine learning models. The reason is that neural networks…