相关论文: Fault Injection and Safe-Error Attack for Extracti…

Given the ubiquity of deep neural networks, it is important that these models do not reveal information about sensitive data that they have been trained on. In model inversion attacks, a malicious user attempts to recover the private…

As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a tremendous concern, which potentially could lead to…

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

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…

We investigate whether model extraction can be used to "steal" the weights of sequential recommender systems, and the potential threats posed to victims of such attacks. This type of risk has attracted attention in image and text…

Network intrusions are a significant problem in all industries today. A critical part of the solution is being able to effectively detect intrusions. With recent advances in artificial intelligence, current research has begun adopting deep…

Graph machine learning has advanced rapidly in tasks such as link prediction, anomaly detection, and node classification. As models scale up, pretrained graph models have become valuable intellectual assets because they encode extensive…

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, the inductive GNNs,…

This article investigates the security issue caused by false data injection attacks in distributed estimation, wherein each sensor can construct two types of residues based on local estimates and neighbor information, respectively. The…

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs).…

Server breaches are an unfortunate reality on today's Internet. In the context of deep neural network (DNN) models, they are particularly harmful, because a leaked model gives an attacker "white-box" access to generate adversarial examples,…

Federated Learning (FL) is a popular collaborative learning scheme involving multiple clients and a server. FL focuses on protecting clients' data but turns out to be highly vulnerable to Intellectual Property (IP) threats. Since FL…

We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such. Given oracle access to a neural network, we introduce a differential attack that can efficiently…

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

Deep neural networks are becoming popular and important assets of many AI companies. However, recent studies indicate that they are also vulnerable to adversarial attacks. Adversarial attacks can be either white-box or black-box. The…

Model extraction is a severe threat to Machine Learning-as-a-Service systems, especially through data-free approaches, where dishonest users can replicate the functionality of a black-box target model without access to realistic data.…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces (APIs). Recent works focus on limited-query budget settings…

Modern advances in sensor, computing, and communication technologies enable various smart grid applications. The heavy dependence on communication technology has highlighted the vulnerability of the electricity grid to false data injection…