Related papers: PRADA: Protecting against DNN Model Stealing Attac…
Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model,…
Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…
Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been…
Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…
Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performance metrics (e.g., desired accuracy, latency). The server…
In this paper we consider the setting where machine learning models are retrained on updated datasets in order to incorporate the most up-to-date information or reflect distribution shifts. We investigate whether one can infer information…
Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable…
Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicious customers to conduct model extraction attacks, i.e.,…
Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries. Though there are some protection options…
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…
Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers. Recent work has shown that attackers can exploit these APIs to extract good approximations of such…
Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…
We introduce the problem of model-extraction attacks in cyber-physical systems in which an attacker attempts to estimate (or extract) the feedback controller of the system. Extracting (or estimating) the controller provides an unmatched…
Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…
Deep neural networks (DNNs) have been widely used in many fields such as images processing, speech recognition; however, they are vulnerable to adversarial examples, and this is a security issue worthy of attention. Because the training…
DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model…
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker…
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…
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…