English
Related papers

Related papers: SEEK: model extraction attack against hybrid secur…

200 papers

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

Cryptography and Security · Computer Science 2025-01-08 Zhang Ruoyan , Zheng Zhongxiang , Bao Wankang

Traditional approaches to vector similarity search over encrypted data rely on fully homomorphic encryption (FHE) to enable computation without decryption. However, the substantial computational overhead of FHE makes it impractical for…

Cryptography and Security · Computer Science 2025-02-21 Dongfang Zhao

Various cryptographic techniques are used in outsourced database systems to ensure data privacy while allowing for efficient querying. This work proposes a definition and components of a new secure and efficient outsourced database system,…

Cryptography and Security · Computer Science 2022-09-20 Dmytro Bogatov

Hybrid Privacy-Preserving Neural Network (HPPNN) implementing linear layers by Homomorphic Encryption (HE) and nonlinear layers by Garbled Circuit (GC) is one of the most promising secure solutions to emerging Machine Learning as a Service…

Cryptography and Security · Computer Science 2020-10-19 Qian Lou , Song Bian , Lei Jiang

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…

Cryptography and Security · Computer Science 2025-06-04 Xueqi Cheng , Minxing Zheng , Shixiang Zhu , Yushun Dong

Homomorphic encryption (HE) has found extensive utilization in federated learning (FL) systems, capitalizing on its dual advantages: (i) ensuring the confidentiality of shared models contributed by participating entities, and (ii) enabling…

Cryptography and Security · Computer Science 2023-08-10 Dongfang Zhao

When neural network model and data are outsourced to cloud server for inference, it is desired to preserve the confidentiality of model and data as the involved parties (i.e., cloud server, model providing client and data providing client)…

Cryptography and Security · Computer Science 2022-06-07 Pinglan Liu , Wensheng Zhang

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

Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard…

Machine Learning · Computer Science 2024-06-14 Avital Shafran , Ilia Shumailov , Murat A. Erdogdu , Nicolas Papernot

Homomorphic encryption (HE) is widely adopted in untrusted environments such as federated learning. A notable limitation of conventional single-key HE schemes is the stringent security assumption regarding collusion between the parameter…

Cryptography and Security · Computer Science 2023-12-29 Dongfang Zhao

A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been…

Information Theory · Computer Science 2023-11-27 Zirui Deng , Vinayak Ramkumar , Rawad Bitar , Netanel Raviv

Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal…

Machine Learning · Computer Science 2024-06-18 Weizhao Jin , Yuhang Yao , Shanshan Han , Jiajun Gu , Carlee Joe-Wong , Srivatsan Ravi , Salman Avestimehr , Chaoyang He

Fully Homomorphic Encryption (FHE) allows for computation directly on encrypted data and enables privacy-preserving neural inference in the cloud. Prior work has focused on models with dense inputs (e.g., CNNs), with less attention given to…

Cryptography and Security · Computer Science 2026-02-23 Karthik Garimella , Austin Ebel , Gabrielle De Micheli , Brandon Reagen

Although homomorphic encryption can be incorporated into neural network layers for securing machine learning tasks, such as confidential inference over encrypted data samples and encrypted local models in federated learning, the…

Cryptography and Security · Computer Science 2022-12-23 Dongfang Zhao

Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet…

Cryptography and Security · Computer Science 2021-06-02 Qian Lou , Lei Jiang

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

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and specialized expertise have historically restricted their wide…

Cryptography and Security · Computer Science 2025-08-28 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

Large Language Models (LLMs) represent valuable intellectual property (IP), reflecting significant investments in training data, compute, and expertise. Deploying these models on partially trusted or insecure devices introduces substantial…

Cryptography and Security · Computer Science 2025-10-30 Racchit Jain , Satya Lokam , Yehonathan Refael , Adam Hakim , Lev Greenberg , Jay Tenenbaum

Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…

Cryptography and Security · Computer Science 2022-10-28 Panagiotis Rizomiliotis , Christos Diou , Aikaterini Triakosia , Ilias Kyrannas , Konstantinos Tserpes

With the evolution of data collection ways, it is possible to produce abundant data described by multiple feature sets. Previous studies show that including more features does not necessarily bring positive effect. How to prevent the…

Machine Learning · Computer Science 2017-11-02 Chenping Hou , Ling-Li Zeng , Dewen Hu