English
Related papers

Related papers: Efficient and Effective Model Extraction

200 papers

Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…

Machine Learning · Computer Science 2022-08-23 Kacem Khaled , Gabriela Nicolescu , Felipe Gohring de Magalhães

Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed…

Cryptography and Security · Computer Science 2025-02-25 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

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

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…

Machine Learning · Computer Science 2022-06-24 Xun Xian , Mingyi Hong , Jie Ding

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

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

Cloud service providers have launched Machine-Learning-as-a-Service (MLaaS) platforms to allow users to access large-scale cloudbased models via APIs. In addition to prediction outputs, these APIs can also provide other information in a…

Cryptography and Security · Computer Science 2022-05-16 Yongjie Wang , Hangwei Qian , Chunyan Miao

A significant number of machine learning models are vulnerable to model extraction attacks, which focus on stealing the models by using specially curated queries against the target model. This task is well accomplished by using part of the…

Cryptography and Security · Computer Science 2023-08-11 Harshit Shah , Aravindhan G , Pavan Kulkarni , Yuvaraj Govidarajulu , Manojkumar Parmar

Model Leeching is a novel extraction attack targeting Large Language Models (LLMs), capable of distilling task-specific knowledge from a target LLM into a reduced parameter model. We demonstrate the effectiveness of our attack by extracting…

Machine Learning · Computer Science 2023-09-20 Lewis Birch , William Hackett , Stefan Trawicki , Neeraj Suri , Peter Garraghan

We study design of black-box model extraction attacks that can send minimal number of queries from a publicly available dataset to a target ML model through a predictive API with an aim to create an informative and distributionally…

Machine Learning · Computer Science 2023-10-19 Pratik Karmakar , Debabrota Basu

Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of queries to the model and then leveraging the model's predictions…

Cryptography and Security · Computer Science 2025-01-03 Yixu Wang , Tianle Gu , Yan Teng , Yingchun Wang , Xingjun Ma

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and…

Machine Learning · Computer Science 2026-03-11 Luxi Lin , Zhihang Lin , Zhanpeng Zeng , Yuhao Chen , Qingyu Zhang , Jixiang Luo , Xuelong Li , Rongrong Ji

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

Deep learning models have been used to support analytics beyond simple aggregation, where deeper and wider models have been shown to yield great results. These models consume a huge amount of memory and computational operations. However,…

Machine Learning · Computer Science 2021-04-22 Shaofeng Cai , Gang Chen , Beng Chin Ooi , Jinyang Gao

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

In many real-world applications, we often need to handle various deployment scenarios, where the resource constraint and the superclass of interest corresponding to a group of classes are dynamically specified. How to efficiently deploy…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Jing Liu , Bohan Zhuang , Mingkui Tan , Xu Liu , Dinh Phung , Yuanqing Li , Jianfei Cai

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's…

Cryptography and Security · Computer Science 2024-12-23 Gaozheng Pei , Shaojie lyu , Ke Ma , Pinci Yang , Qianqian Xu , Yingfei Sun

Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…

Computation and Language · Computer Science 2026-03-05 Lianming Huang , Shangyu Wu , Yufei Cui , Ying Xiong , Haibo Hu , Xue Liu , Tei-Wei Kuo , Nan Guan , Chun Jason Xue

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods. To address this…

Machine Learning · Computer Science 2025-06-10 Jianming Lv , Sijun Xia , Depin Liang , Wei Chen

Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy…

Computer Vision and Pattern Recognition · Computer Science 2022-01-27 Xiaoyong Yuan , Leah Ding , Lan Zhang , Xiaolin Li , Dapeng Wu