English
Related papers

Related papers: Hard-Label Cryptanalytic Extraction of Neural Netw…

200 papers

Deep neural networks (DNNs) are valuable assets, yet their public accessibility raises security concerns about parameter extraction by malicious actors. Recent work by Carlini et al. (crypto'20) and Canales-Mart\'inez et al. (eurocrypt'24)…

Cryptography and Security · Computer Science 2024-10-10 Nicholas Carlini , Jorge Chávez-Saab , Anna Hambitzer , Francisco Rodríguez-Henríquez , Adi Shamir

Deep Neural Networks (DNNs) have attracted significant attention, and their internal models are now considered valuable intellectual assets. Extracting such a model via oracle access to a DNN is conceptually similar to extracting a secret…

Machine Learning · Computer Science 2026-03-30 Akira Ito , Takayuki Miura , Yosuke Todo

The machine learning problem of model extraction was first introduced in 1991 and gained prominence as a cryptanalytic challenge starting with Crypto 2020. For over three decades, research in this field has primarily focused on ReLU-based…

Cryptography and Security · Computer Science 2025-09-23 Yi Chen , Xiaoyang Dong , Ruijie Ma , Yantian Shen , Anyu Wang , Hongbo Yu , Xiaoyun Wang

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…

Machine Learning · Computer Science 2020-07-23 Nicholas Carlini , Matthew Jagielski , Ilya Mironov

Billions of dollars and countless GPU hours are currently spent on training Deep Neural Networks (DNNs) for a variety of tasks. Thus, it is essential to determine the difficulty of extracting all the parameters of such neural networks when…

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

Machine Learning · Computer Science 2020-03-05 Matthew Jagielski , Nicholas Carlini , David Berthelot , Alex Kurakin , Nicolas Papernot

Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protecting their parameters is critical not only for maintaining a…

Cryptography and Security · Computer Science 2025-09-23 Ashley Kurian , Aydin Aysu

During the past decade, Deep Neural Networks (DNNs) proved their value on a large variety of subjects. However despite their high value and public accessibility, the protection of the intellectual property of DNNs is still an issue and an…

Cryptography and Security · Computer Science 2026-04-02 Benoit Coqueret , Mathieu Carbone , Olivier Sentieys , Gabriel Zaid

Model extraction attacks are a kind of attacks in which an adversary obtains a new model, whose performance is equivalent to that of a target model, via query access to the target model efficiently, i.e., fewer datasets and computational…

Cryptography and Security · Computer Science 2020-02-04 Tatsuya Takemura , Naoto Yanai , Toru Fujiwara

Neural network model extraction has recently emerged as an important security concern, as adversaries attempt to recover a network's parameters via black-box queries. Carlini et al. proposed in CRYPTO'20 a model extraction approach,…

Machine Learning · Computer Science 2026-02-19 Haolin Liu , Adrien Siproudhis , Samuel Experton , Peter Lorenz , Christina Boura , Thomas Peyrin

Model extraction is a major threat for embedded deep neural network models that leverages an extended attack surface. Indeed, by physically accessing a device, an adversary may exploit side-channel leakages to extract critical information…

Cryptography and Security · Computer Science 2022-11-11 Raphael Joud , Pierre-Alain Moellic , Simon Pontie , Jean-Baptiste Rigaud

Deep neural networks, costly to train and rich in intellectual property value, are increasingly threatened by model extraction attacks that compromise their confidentiality. Previous attacks have succeeded in reverse-engineering model…

Machine Learning · Computer Science 2024-06-17 Hanna Foerster , Robert Mullins , Ilia Shumailov , Jamie Hayes

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Cryptography and Security · Computer Science 2025-12-19 Eden Luzon , Guy Amit , Roy Weiss , Torsten Kraub , Alexandra Dmitrienko , Yisroel Mirsky

Machine learning models are shown to face a severe threat from Model Extraction Attacks, where a well-trained private model owned by a service provider can be stolen by an attacker pretending as a client. Unfortunately, prior works focus on…

Machine Learning · Computer Science 2021-12-02 Bang Wu , Xiangwen Yang , Shirui Pan , Xingliang Yuan

Model extraction is a growing concern for the security of AI systems. For deep neural network models, the architecture is the most important information an adversary aims to recover. Being a sequence of repeated computation blocks, neural…

Cryptography and Security · Computer Science 2024-02-07 Raphael Joud , Pierre-Alain Moellic , Simon Pontie , Jean-Baptiste Rigaud

As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that deploy neural networks embedded in physical devices may wish to…

Cryptography and Security · Computer Science 2020-06-23 Xing Hu , Ling Liang , Lei Deng , Shuangchen Li , Xinfeng Xie , Yu Ji , Yufei Ding , Chang Liu , Timothy Sherwood , Yuan Xie

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural…

Machine Learning · Computer Science 2021-07-19 Long Kiu Chung , Adam Dai , Derek Knowles , Shreyas Kousik , Grace X. Gao

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Cryptography and Security · Computer Science 2024-11-18 Kevin Hector , Pierre-Alain Moellic , Mathieu Dumont , Jean-Max Dutertre

In this paper we investigate formal verification of extracted rules for Neural Networks under a complexity theoretic point of view. A rule is a global property or a pattern concerning a large portion of the input space of a network. These…

Artificial Intelligence · Computer Science 2025-09-23 Adrian Wurm

The multi-million dollar investment required for modern machine learning (ML) has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have…

Cryptography and Security · Computer Science 2026-03-30 Peter Horvath , Ilia Shumailov , Lukasz Chmielewski , Lejla Batina , Yuval Yarom
‹ Prev 1 2 3 10 Next ›