The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privacy. However, in some applications, such as Augmented/Virtual Reality, integrity verification of the outsourced ML tasks is more critical--a facet that has not received much attention. Existing solutions, such as multi-party computation and proof-based systems, impose significant computation overhead, which makes them unfit for real-time applications. We propose Fides, a novel framework for real-time integrity validation of ML-as-a-Service (MLaaS) inference. Fides features a novel and efficient distillation technique--Greedy Distillation Transfer Learning--that dynamically distills and fine-tunes a space and compute-efficient verification model for verifying the corresponding service model while running inside a trusted execution environment. Fides features a client-side attack detection model that uses statistical analysis and divergence measurements to identify, with a high likelihood, if the service model is under attack. Fides also offers a re-classification functionality that predicts the original class whenever an attack is identified. We devised a generative adversarial network framework for training the attack detection and re-classification models. The evaluation shows that Fides achieves an accuracy of up to 98% for attack detection and 94% for re-classification.
Validation Methods for Energy Time Series Scenarios from Deep Generative Models
Forschungszentrum Jülich GmbH, Institute of Energy and Climate Research, Energy Systems Engineering (IEK-10)(于利希研究中心有限公司,能源与气候研究所,能源系统工程(IEK-10));RWTH Aachen University(亚琛工业大学);Forschungszentrum Jülich GmbH, Institute of Energy and Climate Research, Systems Analysis and Technology Evaluation (IEK-STE)(于利希研究中心有限公司,能源与气候研究所,系统分析与技术评估(IEK-STE));Institute for Theoretical Physics, University of Cologne(科隆大学理论物理研究所);German Aerospace Center (DLR), Institute of Networked Energy Systems(德国航空航天中心,网络化能源系统研究所);Department of Computer Science, OsloMet – Oslo Metropolitan University(奥斯陆城市大学计算机科学系);JARA-ENERGY;RWTH Aachen University, Process Systems Engineering (AVT.SVT)(亚琛工业大学,过程系统工程(AVT.SVT));School of Mathematical Sciences, Queen Mary University of London(伦敦玛丽女王大学数学科学学院);Faculty of Science and Technology, Norwegian University of Life Sciences(挪威生命科学大学科学与技术学院)
Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A
Centre for Cognitive Machines and Computational Health (CMaCH)(认知机器与计算健康中心);School of Computer Science(计算机科学学院);Shanghai Jiao Tong University(上海交通大学);QuietD Biotech(QuietD生物科技)
Inverse Materials Design by Large Language Model-Assisted Generative Framework
School of Software Engineering, South China University of Technology(华南理工大学软件工程学院);The University of Hong Kong(香港大学);City University of Hong Kong(香港城市大学);DP Technology(DP科技);Institute of Physics, Chinese Academy of Sciences(中国科学院物理研究所);AI for Science Institute, Beijing(北京科学智能研究院)
Generative Adversarial Networks for Bitcoin Data Augmentation
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)(巴斯克研究与技术联盟(BRTA)维康特克基金会);Institute of Smart Cities, Public University of Navarre(纳瓦拉公立大学智慧城市学院)
A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validation
University of Bath(巴斯大学);Loughborough University(拉夫堡大学)
Trustworthy AI-Generative Content for Intelligent Network Service: Robustness, Security, and Fairness
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Disease
Vironix Health Inc(Vironix健康公司);University of Oxford(牛津大学);University of Cambridge(剑桥大学);Stanford University(斯坦福大学);University of Southern California(南加州大学)