paper-with-me

홈 › Papers

SEEK: model extraction attack against hybrid secure inference protocols

2022-09-14 · Si Chen, Junfeng Fan

Security concerns about a machine learning model used in a prediction-as-a-service include the privacy of the model, the query and the result. Secure inference solutions based on homomorphic encryption (HE) and/or multiparty computation (MPC) have been developed to protect all the sensitive information. One of the most efficient type of solution utilizes HE for linear layers, and MPC for non-linear layers. However, for such hybrid protocols with semi-honest security, an adversary can malleate the intermediate features in the inference process, and extract model information more effectively than methods against inference service in plaintext. In this paper, we propose SEEK, a general extraction method for hybrid secure inference services outputing only class labels. This method can extract each layer of the target model independently, and is not affected by the depth of the model. For ResNet-18, SEEK can extract a parameter with less than 50 queries on average, with average error less than $0.03\%$.

📄 PDF Abstract BibTeX arXiv:2209.06373

Code (0)

등록된 구현이 없습니다.

Tasks

Model extraction

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction

2025-03-17 · Tong Zhou, Shijin Duan, Gaowen Liu, Charles Fleming 외

Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks threaten these assets by enabling unauthor…

Model extraction

Meta Federated Learning

2021-02-10 · Omid Aramoon, Pin-Yu Chen, Gang Qu, Yuan Tian

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adver…

Federated LearningPrivacy Preserving

PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models

2022-09-13 · William Hackett, Stefan Trawicki, Zhengxin Yu, Neeraj Suri 외

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 extr…

Adversarial AttackDeep Learning

SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment

2025-10-22 · Tushar Nayan, Ziqi Zhang, Ruimin Sun arxiv

With the increasing deployment of Large Language Models (LLMs) on mobile and edge platforms, securing them against model extraction attacks has become a pressing concern. However, protecting model privacy without sacrifi…

Model extraction

Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustness

2024-04-27 · Ali Reza Ghavamipour, Benjamin Zi Hao Zhao, Oguzhan Ersoy, Fatih Turkmen

Decentralized machine learning (DL) has been receiving an increasing interest recently due to the elimination of a single point of failure, present in Federated learning setting. Yet, it is threatened by the looming thre…

Federated LearningPrivacy Preserving