Skip to content

Booksellers & Trade Customers: Sign up for online bulk buying at trade.atlanticbooks.com for wholesale discounts

Booksellers: Create Account on our B2B Portal for wholesale discounts

ML and Privacy Building Secure Data Models: Ensure privacy in ML with federated learning techniques

by Isandro Myles
Sold out
₹1,776.00
Original price ₹1,776.00
Original price ₹1,776.00
₹1,776.00
Current price ₹1,776.00

Imported Edition - Ships in 18-21 Days

Free Shipping in India on orders above Rs. 500

Request Bulk Quantity Quote
+91
Book cover type: Paperback
  • ISBN13: 9798267491525
  • Binding: Paperback
  • Subject: N/A
  • Publisher: Independently Published
  • Publisher Imprint: Independently Published
  • Publication Date:
  • Pages: 184
  • Original Price: USD 16.99
  • Language: English
  • Edition: N/A
  • Item Weight: 254 grams
  • BISAC Subject(s): Machine Theory

Protecting user data shouldn't slow down machine learning. ML and Privacy: Building Secure Data Models 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 federated learning, differential privacy, and secure aggregation with clear examples and checklists you can apply immediately.

You'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.

What you'll learn

  • Map data flows and apply minimization, pseudonymization, and purpose limits

  • Train at the edge with federated learning and server-side secure aggregation

  • Use differential privacy (ε/δ) with practical budgeting and utility checks

  • Reduce exposure with split learning, TEEs/confidential computing (overview)

  • Prevent leakage: membership inference, inversion, and reconstruction defenses

  • Govern features, labels, and releases with versioning and lineage

  • Operate with evidence: consent tracking, retention, redaction, and audits

Who it's for
ML engineers, data scientists, privacy engineers, architects, and product leaders who need privacy-preserving results without derailing delivery.

What's inside
Copy-ready patterns, policy-to-pipeline templates, risk rubrics, and lightweight dashboards for privacy/utility balance.

Trusted for over 49 years

Family Owned Company

Secure Payment

All Major Credit Cards/Debit Cards/UPI & More Accepted

New & Authentic Products

India's Largest Distributor

Need Support?

Whatsapp Us