secureai-lab.com
Open in
urlscan Pro
103.163.218.106
Public Scan
URL:
https://secureai-lab.com/
Submission: On July 10 via automatic, source certstream-suspicious — Scanned from DE
Submission: On July 10 via automatic, source certstream-suspicious — Scanned from DE
Form analysis 0 forms found in the DOM
Text Content
+84367139457 tutran@secureai-lab.com About usResearchPublicationsSolutionsTeachingFundingResourceBlogContact EXPLORING AI SAFETY FOR A SECURE TOMORROW We research, construct and test data privacy and security for artificial intelligence-based applications at the Secure AI Lab. Our objectives focuses on developing safe and secure technologies for AI-driven apps and user data. Our goal is to ease the process for developers to build and improve AI systems that prioritize privacy, security, and resilience. RESEARCH AREAS Privacy for Machine Learning as a Service (MLaaS) Security Threats in Machine Learning Systems Explainable AI AI Ethcis Ensure Secure and Robustness of Machine learning System Privacy Preserving Technique Primitives Privacy Preserving Collaborative Learning Privacy for Machine Learning as a Service (MLaaS) Security Threats in Machine Learning Systems Explainable AI AI Ethcis Ensure Secure and Robustness of Machine learning System Privacy Preserving Technique Primitives Privacy Preserving Collaborative Learning Privacy for Machine Learning as a Service (MLaaS) Security Threats in Machine Learning Systems Explainable AI AI Ethcis NEWS 28/09/2023 The foundation of Secure AI Lab is built upon a commitment to advancing the frontiers of artificial intelligence while ensuring the utmost security, privacy, and ethical standards in the development and deployment of AI technologies. 11/10/2023 The announcement of Secure AI Lab's research topic underscores our dedication to addressing critical challenges in AI security and ensuring the responsible and secure development of artificial intelligence technologies. 28/01/2024 The paper "A Comprehensive Survey and Taxonomy on Privacy-Preserving Deep Learning" have been accepted to publish in Neurocomputing Journal. PUBLICATIONS AN EFFICIENT APPROACH FOR PRIVACY PRESERVING DECENTRALIZED DEEP LEARNING MODELS BASED ON SECURE MULTI-PARTY COMPUTATION Anh-Tu Tran, The-Dung Luong, Jessada Karnjana, Van-Nam Huynh Published 21/01/2021 at Neurocomputing, Volume 422, 2021, Pages 245-262 Paper DEEP MODELS WITH DIFFERENTIAL PRIVACY FOR DISTRIBUTED WEB ATTACK DETECTION Anh-Tu Tran, The Dung Luong, Xuan Sang Pham, Thi Luong Tran Published 19/10/2022 at 2022 14th International Conference on Knowledge and Systems Engineering (KSE), Nha Trang, Vietnam, 2022, pp. 1-6, doi: 10.1109/KSE56063.2022.9953788. Paper SECURE INFERENCE VIA DEEP LEARNING AS A SERVICE WITHOUT PRIVACY LEAKAGE Anh-Tu Tran, The-Dung Luong, Cong-Chieu Ha, Duc-Tho Hoang, Thi-Luong Tran Published 19/08/2021 at 2021 RIVF International Conference on Computing and Communication Technologies (RIVF), 2021 Paper VQC-COVID-NET: VECTOR QUANTIZATION CONTRASTIVE LEARNING FOR COVID-19 IMAGE BASE CLASSIFICATION Linh Trinh, Bach Ha, Anh Tu Tran Published 31/10/2022 at 2022 9th NAFOSTED Conference on Information and Computer Science (NICS), Ho Chi Minh City, Vietnam, 2022, pp. 247-251, doi: 10.1109/NICS56915.2022.10013439. Paper