English
Related papers

Related papers: Beyond Labeling Oracles: What does it mean to stea…

200 papers

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

Machine Learning (ML) models become vulnerable to Model Stealing Attacks (MSA) when they are deployed as a service. In such attacks, the deployed model is queried repeatedly to build a labelled dataset. This dataset allows the attacker to…

Machine Learning · Computer Science 2023-11-09 Akshit Jindal , Vikram Goyal , Saket Anand , Chetan Arora

We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces (APIs). Recent works focus on limited-query budget settings…

Computation and Language · Computer Science 2023-10-24 Chengwei Dai , Minxuan Lv , Kun Li , Wei Zhou

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

Cryptography and Security · Computer Science 2023-11-27 Gopichandh Golla

Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property of ML models has emerged as an important consideration.…

Machine Learning · Computer Science 2020-05-28 Buse Gul Atli , Sebastian Szyller , Mika Juuti , Samuel Marchal , N. Asokan

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…

The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counterfactual explanations, inadvertently increase the risk of…

Machine Learning · Computer Science 2025-10-24 Awa Khouna , Julien Ferry , Thibaut Vidal

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

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…

Cryptography and Security · Computer Science 2025-08-11 Yash More , Prakhar Ganesh , Golnoosh Farnadi

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

Compared to traditional neural networks with a single output channel, a multi-exit network has multiple exits that allow for early outputs from the model's intermediate layers, thus significantly improving computational efficiency while…

Cryptography and Security · Computer Science 2025-03-18 Li Pan , Lv Peizhuo , Chen Kai , Zhang Shengzhi , Cai Yuling , Xiang Fan

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…

Computation and Language · Computer Science 2021-03-19 Xuanli He , Lingjuan Lyu , Qiongkai Xu , Lichao Sun

In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability…

Cryptography and Security · Computer Science 2022-06-08 Huiyu Li , Nicholas Ayache , Hervé Delingette

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model,…

Cryptography and Security · Computer Science 2017-04-04 Reza Shokri , Marco Stronati , Congzheng Song , Vitaly Shmatikov

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Cryptography and Security · Computer Science 2023-02-24 Boyang Zhang , Xinlei He , Yun Shen , Tianhao Wang , Yang Zhang

Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…

Cryptography and Security · Computer Science 2021-10-07 Yugeng Liu , Rui Wen , Xinlei He , Ahmed Salem , Zhikun Zhang , Michael Backes , Emiliano De Cristofaro , Mario Fritz , Yang Zhang

Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show…

Machine Learning · Computer Science 2024-05-31 Martin Bertran , Shuai Tang , Michael Kearns , Jamie Morgenstern , Aaron Roth , Zhiwei Steven Wu

Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that…

Machine Learning · Computer Science 2017-11-16 Yannic Kilcher , Thomas Hofmann

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

Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the…

Machine Learning · Computer Science 2024-07-19 Ana-Maria Creţu , Florent Guépin , Yves-Alexandre de Montjoye