English
Related papers

Related papers: PRADA: Protecting against DNN Model Stealing Attac…

200 papers

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,…

Cryptography and Security · Computer Science 2025-09-01 Daryna Oliynyk , Rudolf Mayer , Kathrin Grosse , Andreas Rauber

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…

Cryptography and Security · Computer Science 2025-06-04 Xueqi Cheng , Minxing Zheng , Shixiang Zhu , Yushun Dong

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…

Cryptography and Security · Computer Science 2024-01-30 Peizhuo Lv , Hualong Ma , Kai Chen , Jiachen Zhou , Shengzhi Zhang , Ruigang Liang , Shenchen Zhu , Pan Li , Yingjun Zhang

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…

Machine Learning · Computer Science 2022-02-09 Ji Gao , Sanjam Garg , Mohammad Mahmoody , Prashant Nalini Vasudevan

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…

Cryptography and Security · Computer Science 2023-08-08 Debopam Sanyal , Jui-Tse Hung , Manav Agrawal , Prahlad Jasti , Shahab Nikkhoo , Somesh Jha , Tianhao Wang , Sibin Mohan , Alexey Tumanov

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…

Machine Learning · Computer Science 2024-01-04 Tian Hui , Farhad Farokhi , Olga Ohrimenko

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 · Computer Science 2022-06-30 Adam Dziedzic , Nikita Dhawan , Muhammad Ahmad Kaleem , Jonas Guan , Nicolas Papernot

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.,…

Cryptography and Security · Computer Science 2023-06-14 Shiqian Zhao , Kangjie Chen , Meng Hao , Jian Zhang , Guowen Xu , Hongwei Li , Tianwei Zhang

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…

Cryptography and Security · Computer Science 2020-11-03 Haonan Yan , Xiaoguang Li , Hui Li , Jiamin Li , Wenhai Sun , Fenghua Li

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 · Computer Science 2025-03-11 Daryna Oliynyk , Rudolf Mayer , Andreas Rauber

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…

Machine Learning · Computer Science 2021-07-13 Soham Pal , Yash Gupta , Aditya Kanade , Shirish Shevade

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…

Machine Learning · Computer Science 2025-10-23 Xiaoyu Wu , Yifei Pang , Terrance Liu , Zhiwei Steven Wu

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…

Machine Learning · Computer Science 2023-04-27 Momina Sajid , Yanning Shen , Yasser Shoukry

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…

Machine Learning · Statistics 2021-02-18 Sasi Kumar Murakonda , Reza Shokri , George Theodorakopoulos

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…

Cryptography and Security · Computer Science 2019-08-08 Wenjian Luo , Chenwang Wu , Nan Zhou , Li Ni

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…

Cryptography and Security · Computer Science 2023-08-03 Xiaobei Yan , Xiaoxuan Lou , Guowen Xu , Han Qiu , Shangwei Guo , Chip Hong Chang , Tianwei Zhang

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…

Cryptography and Security · Computer Science 2019-09-20 Jinyuan Jia , Neil Zhenqiang Gong

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…

Machine Learning · Statistics 2019-08-27 Liwei Song , Reza Shokri , Prateek Mittal

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…

Machine Learning · Computer Science 2020-04-21 Yuheng Zhang , Ruoxi Jia , Hengzhi Pei , Wenxiao Wang , Bo Li , Dawn Song

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…

Machine Learning · Computer Science 2024-05-20 Guy Amit , Mosh Levy , Yisroel Mirsky