<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Differential-Privacy on Pi Stack</title>
    <link>https://www.pistack.xyz/tags/differential-privacy/</link>
    <description>Recent content in Differential-Privacy on Pi Stack</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 13 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.pistack.xyz/tags/differential-privacy/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Self-Hosted Differential Privacy Engines: Google DP vs OpenDP vs SmartNoise</title>
      <link>https://www.pistack.xyz/posts/2026-06-13-self-hosted-differential-privacy-engines-google-dp-opendp-smartnoise/</link>
      <pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://www.pistack.xyz/posts/2026-06-13-self-hosted-differential-privacy-engines-google-dp-opendp-smartnoise/</guid>
      <description>&lt;h2 id=&#34;what-is-differential-privacy&#34;&gt;What Is Differential Privacy?&lt;/h2&gt;&#xA;&lt;p&gt;Differential privacy is a mathematical framework for quantifying the privacy guarantees of data analysis algorithms. It ensures that the output of a computation does not reveal whether any single individual&amp;rsquo;s data was included in the input. This is achieved by adding carefully calibrated noise to query results, making it impossible to infer specific records while preserving aggregate statistical properties.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
