3 Review(s)

Gain hands-on experience of data privacy and privacy preserved machine learning with open source ML frame works. Discover privacy preserving techniques and algorithms to protect sensitive data from privacy breaches.Key FeaturesUnderstand ML privacy risks, employ algorithms safeguarding data against breachesDevelop and deploy privacy preserving ML pipelines using open source frameworksGain insights into confidential computing and its role in countering memory-based data attacksBook DescriptionPrivacy regulations are evolving each year and compliance to privacy regulations are mandatory for every enterprise. At the same time Machine Learning Engineers need to analyze large amounts of data to predict various insights and be compliant with privacy regulations to protect the sensitive data. This is quite challenging because of large volumes of data, and lack of in-depth expertise in Privacy Preserved Machine Learning.This book imparts knowledge on data privacy, machine learning privacy threats, and real-world cases of privacy-preserved machine learning, along with open source frameworks for implementation. Unique in its kind, it guides readers in developing anti-money laundering solutions via Federated Learning and Differential Privacy. It addresses data-in-memory attacks and strategies for safeguarding data and ML models. The book concludes by discussing the necessity of confidential computation, privacy preserved machine learning benchmarks, and cutting-edge research.What you will learnStudy data privacy, threats, and attacks across ML phases for comprehensive understandingExplore Uber and Apple cases for applying differential privacy, enhancing data securityLearn IID, Non-IID data sets and data categoriesUtilize open-source tools for Federated Learning, grasp FL algorithms and benchmarksMaster secure multiparty computation with PSI for large dataUnderstand confidential computation and know how it helps data in memory attacksWho this book is forThis book is for Data Scientists, Machine Learning Engineers, Privacy Engineers who have working knowledge in mathematics, have basic knowledge in any one of the ML Frameworks (TensorFlow, PyTorch, Scikit Learning). This book helps to develop ML pipelines in a privacy preserved manner and comply with data privacy regulations (CCPA, GDPR) across the world.