相关论文: MAZE: Data-Free Model Stealing Attack Using Zeroth…

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

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…

GAN is a deep-learning based generative approach to generate contents such as images, languages and speeches. Recently, studies have shown that GAN can also be applied to generative adversarial attack examples to fool the machine-learning…

Responding to user data deletion requests, removing noisy examples, or deleting corrupted training data are just a few reasons for wanting to delete instances from a machine learning (ML) model. However, efficiently removing this data from…

We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample…

With growing popularity, deep learning (DL) models are becoming larger-scale, and only the companies with vast training datasets and immense computing power can manage their business serving such large models. Most of those DL models are…

Neural backdoor attack is emerging as a severe security threat to deep learning, while the capability of existing defense methods is limited, especially for complex backdoor triggers. In the work, we explore the space formed by the pixel…

Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and other sophisticated threats. Many practical black-box MIAs…

Malware detectors based on machine learning (ML) have been shown to be susceptible to adversarial malware examples. However, current methods to generate adversarial malware examples still have their limits. They either rely on detailed…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation. These attacks pose great threats to the applications of…

Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been…

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…

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…

An adversary who aims to steal a black-box model repeatedly queries the model via a prediction API to learn a function that approximates its decision boundary. Adversarial approximation is non-trivial because of the enormous combinations of…

Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to…

Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. It is challenging to timely prevent such model-stealing attacks to achieve strong protection and maintain…

Machine learning as a Service (MLaaS) allows users to query the machine learning model in an API manner, which provides an opportunity for users to enjoy the benefits brought by the high-performance model trained on valuable data. This…