English
Related papers

Related papers: Cryptanalytic Extraction of Neural Network Models

200 papers

Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS…

Cryptography and Security · Computer Science 2024-09-25 Hongyu Zhu , Wentao Hu , Sichu Liang , Fangqi Li , Wenwen Wang , Shilin Wang

Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-parameters of a targeted DL model. Existing extraction attack…

Cryptography and Security · Computer Science 2023-02-01 William Hackett , Stefan Trawicki , Zhengxin Yu , Neeraj Suri , Peter Garraghan

We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model. Assuming that both the adversary and victim model…

Computation and Language · Computer Science 2020-10-13 Kalpesh Krishna , Gaurav Singh Tomar , Ankur P. Parikh , Nicolas Papernot , Mohit Iyyer

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 attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

Cryptography and Security · Computer Science 2025-07-09 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

Model extraction attacks have become serious issues for service providers using machine learning. We consider an adversarial setting to prevent model extraction under the assumption that attackers will make their best guess on the service…

Machine Learning · Computer Science 2021-03-12 Yuto Mori , Atsushi Nitanda , Akiko Takeda

The choice of parameters in neural networks is crucial in the performance, and an oracle distribution derived from the ridgelet transform enables us to obtain suitable initial parameters. In other words, the distribution of parameters is…

Machine Learning · Computer Science 2024-11-18 Hikaru Homma , Jun Ohkubo

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model…

Machine Learning · Computer Science 2020-05-29 Muhammad A. Shah , Raphael Olivier , Bhiksha Raj

MLaaS Service Providers (SPs) holding a Neural Network would like to keep the Neural Network weights secret. On the other hand, users wish to utilize the SPs' Neural Network for inference without revealing their data. Multi-Party…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Yakir Gorski , Amir Jevnisek , Shai Avidan

Deep learning is gaining importance in many applications. However, Neural Networks face several security and privacy threats. This is particularly significant in the scenario where Cloud infrastructures deploy a service with Neural Network…

Cryptography and Security · Computer Science 2019-07-09 Vasisht Duddu , Debasis Samanta , D Vijay Rao , Valentina E. Balas

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction…

Machine Learning · Computer Science 2019-05-23 Soham Pal , Yash Gupta , Aditya Shukla , Aditya Kanade , Shirish Shevade , Vinod Ganapathy

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…

Cryptography and Security · Computer Science 2022-11-01 Xuanli He , Chen Chen , Lingjuan Lyu , Qiongkai Xu

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…

Cryptography and Security · Computer Science 2016-10-04 Florian Tramèr , Fan Zhang , Ari Juels , Michael K. Reiter , Thomas Ristenpart

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

Cryptography and Security · Computer Science 2023-09-06 Bargav Jayaraman , Esha Ghosh , Melissa Chase , Sambuddha Roy , Wei Dai , David Evans

Kernel-based methods enjoy powerful generalization capabilities in handling a variety of learning tasks. When such methods are provided with sufficient training data, broadly-applicable classes of nonlinear functions can be approximated…

Machine Learning · Statistics 2017-12-29 Fatemeh Sheikholeslami , Dimitris Berberidis , Georgios B. Giannakis

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

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Machine Learning · Statistics 2019-11-19 Sanjay Kariyappa , Moinuddin K Qureshi

The verification problem for neural networks is verifying whether a neural network will suffer from adversarial samples, or approximating the maximal allowed scale of adversarial perturbation that can be endured. While most prior work…

Machine Learning · Computer Science 2018-11-16 Qinglong Wang , Kaixuan Zhang , Xue Liu , C. Lee Giles

This paper introduces a novel data-free model extraction attack that significantly advances the current state-of-the-art in terms of efficiency, accuracy, and effectiveness. Traditional black-box methods rely on using the victim's model as…

Cryptography and Security · Computer Science 2024-10-22 Maor Biton Dor , Yisroel Mirsky

Along with the advent of deep neural networks came various methods of exploitation, such as fooling the classifier or contaminating its training data. Another such attack is known as model extraction, where provided API access to some black…

Machine Learning · Computer Science 2019-12-18 David DeFazio , Arti Ramesh