English
Related papers

Related papers: Efficient Model Extraction via Boundary Sampling

200 papers

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

Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of such "victim" models based solely on blackbox interactions:…

Computer Vision and Pattern Recognition · Computer Science 2018-12-10 Tribhuvanesh Orekondy , Bernt Schiele , Mario Fritz

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

Model Extraction attacks exploit the target model's prediction API to create a surrogate model in order to steal or reconnoiter the functionality of the target model in the black-box setting. Several recent studies have shown that a…

Machine Learning · Computer Science 2022-02-25 Amir Mahdi Sadeghzadeh , Amir Mohammad Sobhanian , Faezeh Dehghan , Rasool Jalili

Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…

Computer Vision and Pattern Recognition · Computer Science 2019-06-12 Ziang Yan , Yiwen Guo , Changshui Zhang

Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect…

Cryptography and Security · Computer Science 2022-04-26 Sunandini Sanyal , Sravanti Addepalli , R. Venkatesh Babu

Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder…

Cryptography and Security · Computer Science 2024-09-18 Jonathan Rosenthal , Shanchao Liang , Kevin Zhang , Lin Tan

We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or…

Machine Learning · Statistics 2021-04-30 Thomas Brunner , Frederik Diehl , Michael Truong Le , Alois Knoll

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

Machine Learning · Computer Science 2023-09-12 Kacem Khaled , Mouna Dhaouadi , Felipe Gohring de Magalhães , Gabriela Nicolescu

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Wenxuan Wang , Bangjie Yin , Taiping Yao , Li Zhang , Yanwei Fu , Shouhong Ding , Jilin Li , Feiyue Huang , Xiangyang Xue

In model extraction attacks, the goal is to reveal the parameters of a black-box machine learning model by querying the model for a selected set of data points. Due to an increasing demand for explanations, this may involve counterfactual…

Optimization and Control · Mathematics 2026-03-04 Daan Otto , Jannis Kurtz , Dick den Hertog , Ilker Birbil

The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers. Model extraction attacks, particularly query-based…

Cryptography and Security · Computer Science 2023-12-25 Zeyu Li , Chenghui Shi , Yuwen Pu , Xuhong Zhang , Yu Li , Jinbao Li , Shouling Ji

The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye. While offering new creative and…

Machine Learning · Computer Science 2025-08-26 Haoyue Bai , Yiyou Sun , Wei Cheng , Haifeng Chen

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

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

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

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Chen Ma , Li Chen , Jun-Hai Yong

For black-box attacks, the gap between the substitute model and the victim model is usually large, which manifests as a weak attack performance. Motivated by the observation that the transferability of adversarial examples can be improved…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Yuyang Long , Qilong Zhang , Boheng Zeng , Lianli Gao , Xianglong Liu , Jian Zhang , Jingkuan Song

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Tao Xiang , Hangcheng Liu , Shangwei Guo , Tianwei Zhang , Xiaofeng Liao

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