{"id":387755,"date":"2024-10-01T16:24:49","date_gmt":"2024-10-01T22:24:49","guid":{"rendered":"http:\/\/xianblog.wordpress.com\/?p=57441"},"modified":"2024-10-01T16:24:49","modified_gmt":"2024-10-01T22:24:49","slug":"hands-on-differential-privacy-book-review","status":"publish","type":"post","link":"https:\/\/www.r-bloggers.com\/2024\/10\/hands-on-differential-privacy-book-review\/","title":{"rendered":"Hands-On Differential Privacy [book review]"},"content":{"rendered":"\r\n\r\n
\r\n[This article was first published on R \u2013 Xi'an's Og<\/a><\/strong>, and kindly contributed to R-bloggers<\/a>]. (You can report issue about the content on this page here<\/a>)\r\n
Want to share your content on R-bloggers? click here<\/a> if you have a blog, or here<\/a> if you don't.\r\n<\/div>\n

<\/a>Hands-On Differential Privacy<\/a> was published just a few months ago (from September\u00a0 2024!) by (the US publisher) O\u2019Reilly<\/a>, famous for its programming and technical books with animal covers! A slate pencil sea urchin<\/em> in the present case<\/a>. The book<\/a> is indeed classical O\u2019Reilly\u2019s<\/a>, with lots of notes, little theory (or maths!) and symbols, a loose structuring of the chapters (no section numbers) and highly detailed examples, and of course plenty of OpenDP code inserts. For instance, in the present case<\/a>, a case study about the privatization of a sample average x\u0304 that takes about ten pages. Terrible equation rendering btw (what\u2019s wrong with LA<\/sup>TE<\/sub>X?!).\u00a0 Overall, I am quickly lost in most of the chapters due to a lack of a driving narrative, facing instead a catalogue of possible scenari and procedures, appearing one after the other as in a fashion show.<\/p>\n

Hands-On Differential Privacy<\/a> is written by Ethan Cowan, Michael Shoemate, and Mayana Pereira. I came across the book during the OpenDP workshop<\/a> at Harvard [that took place right after my return from the Pacific Northwest<\/a>] and it is definitely linked with OpenDP<\/a>, all authors being\u00a0 actually involved at one stage or another in the OpenDP Team<\/a>. The style of the book<\/a> is once again in tune with the O\u2019Reilly manuals, which sort of clashes with my preferences. For instance, the introduction of differential privacy (Chapter 2) is quite extensive. Chapter 3 proceeds to teach about private data transform(ation)s, stability (a rewording of Lipschitz-ianity), with code illustrations, often repeating the earlier derivation (see eg p203), while Chapter 4 is its equivalent for private mechanisms. (With the diagrams Figures 3-1 and 4-1 differing only in highlighting\/bolding different functions in a privatized data processing pipeline.) Returning to differential privacy with a privacy loss parameter and to Laplace and exponential mechanisms, Chapter 5 proposes several notions of privacy, all closed under post-processing. This includes Wasserman and Zhou (2010) interpretation of privacy as hypothesis testing, except it is not exploited further than connecting type I and type II with (\u03b5,\u03b4) parameters. Chapter 6 concludes Part I about concepts with a series of (fearless) combinators, keeping stability and privacy. With an increasing proportion of coding excerpts which I [imho] did not find particularly helpful.<\/p>\n

<\/a>Nothing about statistical loss of information or efficiency, bias, &tc. until Chapter 8 (p199) and even then so little. Part II is about practice, with a first Chapter\u00a0 7 on setting a privacy unit (e.g., a person-month) before ensuring their privacy is protected. And discussing unbounded contributions (not unbounded data!). While Chapter 8 very thinly covers statistical modelling, while remaining agnostic about the choice of statistical procedures (Bayes being solely and na\u00efvely mentioned for classification, furthermore with data-based evaluation of the class \u201cprior\u201d probabilities, p211). At this stage, procedures are often only defined through spinets of code, like the private Theil-Sen estimator (pp204-205). The continuous case boils to a Normality assumption, with its pmf being defined (p212) as<\/p>\n

\"\\text{Pr}(x=\\mu)=\\frac{1}{\\sqrt{2\\pi\\sigma}}e^{-(x-\\mu)\/2\\sigma^2}\"<\/p>\n

which contains at least three errors! Chapter 9 is the equivalent of Chapter 8 for machine learning, mostly centred on private gradient descent. And a Pytorch section (pp232-235). Completed by a light Chapter 10 on synthetic data, which does not seem to broach upon the issue of large dimension covariates, providing instead a list of GAN synthetizers.<\/p>\n

Part III (Deploying differential privacy) is even more about practice, with Chapter 11 on privacy attacks, Chapter 12 on calibrating a privacy mechanism (co-written with Jayshree Sarathy), and good practice (like codebooks and data annotations), with the appearance of contextual integrity I discovered if not perfectly understood last year at the BIRS workshop<\/a> in Kelowna<\/a>. And Chapter 13 on planning a privacy project, with an 11 step checklist, most of which are quite vague [imho] and do include strategies to make the data owners confident their privacy is safe.<\/p>\n

[Disclaimer about potential self-plagiarism: this post or an edited version will eventually appear in my Books Review section<\/a> in CHANCE<\/a>]<\/em><\/p>\n\n

\r\n
To leave a comment<\/strong> for the author, please follow the link and comment on their blog: R \u2013 Xi'an's Og<\/a><\/strong>.<\/div>\r\n
\r\nR-bloggers.com<\/a> offers daily e-mail updates<\/a><\/strong> about R<\/a> news and tutorials about learning R<\/a> and many other topics. Click here if you're looking to post or find an R\/data-science job<\/a>.\r\n\r\n
Want to share your content on R-bloggers? click here<\/a> if you have a blog, or here<\/a> if you don't.\r\n<\/div>","protected":false},"excerpt":{"rendered":"
Hands-On Differential Privacy was published just a few months ago (from September\u00a0 2024!) by (the US publisher) O\u2019Reilly, famous for its programming and technical books with animal covers! A slate pencil sea urchin in the present case. The book is indeed classical O\u2019Reilly\u2019s, with lots of notes, little …<\/div>\n
<\/div>\n
<\/div>\n","protected":false},"author":56,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[],"aioseo_notices":[],"jetpack-related-posts":[],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/posts\/387755"}],"collection":[{"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/users\/56"}],"replies":[{"embeddable":true,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/comments?post=387755"}],"version-history":[{"count":1,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/posts\/387755\/revisions"}],"predecessor-version":[{"id":387756,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/posts\/387755\/revisions\/387756"}],"wp:attachment":[{"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/media?parent=387755"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/categories?post=387755"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.r-bloggers.com\/wp-json\/wp\/v2\/tags?post=387755"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}