{"product_id":"ml-and-privacy-building-secure-data-models-ensure-privacy-in-ml-with-federated-learning-techniques-9798267491525","title":"ML and Privacy Building Secure Data Models: Ensure privacy in ML with federated learning techniques","description":"\u003cp\u003e • Author(s): Isandro Myles\u003cbr\u003e • Publisher: Independently Published\u003cbr\u003e • Publisher Imprint: Independently Published\u003cbr\u003e • BISAC: Machine Theory\u003c\/p\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003eProtecting user data shouldn't slow down machine learning. \u003cb\u003eML and Privacy: Building Secure Data Models\u003c\/b\u003e gives engineers, data scientists, and privacy teams a practical playbook for training and deploying models while keeping sensitive information safe. Starting from first principles-data minimization, threat models, and risk scoring-you'll implement \u003cb\u003efederated learning\u003c\/b\u003e, \u003cb\u003edifferential privacy\u003c\/b\u003e, and \u003cb\u003esecure aggregation\u003c\/b\u003e with clear examples and checklists you can apply immediately.\u003c\/p\u003e\u003cp\u003eYou'll learn how to pick privacy budgets you can explain, reduce leakage risks, and measure utility so stakeholders understand trade-offs. The book closes with pipelines and evidence: logging, consent signals, retention limits, and audits that stand up to scrutiny.\u003c\/p\u003e\u003cp\u003e\u003cb\u003eWhat you'll learn\u003c\/b\u003e\u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e\u003cp\u003eMap data flows and apply minimization, pseudonymization, and purpose limits\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003eTrain at the edge with \u003cb\u003efederated learning\u003c\/b\u003e and server-side \u003cb\u003esecure aggregation\u003c\/b\u003e\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003eUse \u003cb\u003edifferential privacy\u003c\/b\u003e (ε\/δ) with practical budgeting and utility checks\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003eReduce exposure with split learning, TEEs\/confidential computing (overview)\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003ePrevent leakage: membership inference, inversion, and reconstruction defenses\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003eGovern features, labels, and releases with versioning and lineage\u003c\/p\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cp\u003eOperate with evidence: consent tracking, retention, redaction, and audits\u003c\/p\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003e\u003cb\u003eWho it's for\u003c\/b\u003e\u003cbr\u003eML engineers, data scientists, privacy engineers, architects, and product leaders who need privacy-preserving results without derailing delivery.\u003c\/p\u003e\u003cp\u003e\u003cb\u003eWhat's inside\u003c\/b\u003e\u003cbr\u003eCopy-ready patterns, policy-to-pipeline templates, risk rubrics, and lightweight dashboards for privacy\/utility balance.\u003c\/p\u003e","brand":"Independently Published","offers":[{"title":"Paperback","offer_id":47594511007895,"sku":"9798267491525","price":1776.0,"currency_code":"INR","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0666\/3471\/1191\/files\/9798267491525.webp?v=1774986220","url":"https:\/\/atlanticbooks.com\/products\/ml-and-privacy-building-secure-data-models-ensure-privacy-in-ml-with-federated-learning-techniques-9798267491525","provider":"Atlantic Books","version":"1.0","type":"link"}