Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
sfba.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Mastodon instance for the San Francisco Bay Area. Come on in and join us!

Administered by:

Server stats:

2.4K
active users

sfba.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.4

#differentialprivacy

0 posts0 participants0 posts today
Simson Garfinkel<p><a href="https://newsie.social/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> made the top position of @techreview's "Recent books from the MIT community" in the March/April edition.</p><p><a href="https://www.technologyreview.com/2025/02/25/1111216/recent-books-from-the-mit-community-21/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">technologyreview.com/2025/02/2</span><span class="invisible">5/1111216/recent-books-from-the-mit-community-21/</span></a></p>
Vis Lab @ Khoury, Northeastern<p>Congratulations DOCTOR Liudas Panavas on the successful defense of his dissertation "Bridging the Gap: Human Centered Research for Democratizing <a href="https://vis.social/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> " 🎉 and congrats to advisor <span class="h-card" translate="no"><a href="https://vis.social/@codydunne" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>codydunne</span></a></span> ❤️ <a href="https://vis.social/tags/HCI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HCI</span></a> <a href="https://vis.social/tags/DataVisualization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataVisualization</span></a> </p><p><a href="https://lpanavas.github.io/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lpanavas.github.io/</span><span class="invisible"></span></a></p>
Simson Garfinkel<p>I'm talking about <a href="https://newsie.social/tags/differentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>differentialPrivacy</span></a> on the SecureTalk podcast by @StrikeGraph.</p><p>Website: www.securetalkpodcast.com<br>Youtube: <a href="https://youtu.be/eZFgxKsFvYg?si=w62KtsRa4dNGEl3b" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/eZFgxKsFvYg?si=w62Kts</span><span class="invisible">Ra4dNGEl3b</span></a><br>Apple Podcast: <a href="https://podcasts.apple.com/us/podcast/predicting-data-breach-risk-how-mathematical-privacy/id1354145110?i=1000700773770" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">podcasts.apple.com/us/podcast/</span><span class="invisible">predicting-data-breach-risk-how-mathematical-privacy/id1354145110?i=1000700773770</span></a><br>Spotify: <a href="https://open.spotify.com/episode/4o9h8PPy6jnKJzYyLqxUDv" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">open.spotify.com/episode/4o9h8</span><span class="invisible">PPy6jnKJzYyLqxUDv</span></a><br>SoundCloud: <a href="https://soundcloud.com/user-779694357/predicting-data-breach-risk-how-mathematical-privacy-is-revolutionizing-data-sharing" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">soundcloud.com/user-779694357/</span><span class="invisible">predicting-data-breach-risk-how-mathematical-privacy-is-revolutionizing-data-sharing</span></a></p>
Ján Bogár<p>I just found out about <a href="https://mastodonczech.cz/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> and it's awesome.</p><p>It's a way of releasing summaries of private data so that almost no info about any individual is leaked. These summaries can be simple, e.g. mean value, or complex, like trained <a href="https://mastodonczech.cz/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> model.</p><p>E.g. you can train auto-correct on private texts with guarantee that it will not leak during use. How cool is that?</p><p><a href="https://mastodonczech.cz/tags/UScensus" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>UScensus</span></a> also uses it.</p><p>Popular summary here: <a href="https://youtu.be/pT19VwBAqKA" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/pT19VwBAqKA</span><span class="invisible"></span></a></p><p>Introductory lecture: <a href="https://youtu.be/9lqd2UINW-E" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/9lqd2UINW-E</span><span class="invisible"></span></a></p>
The New Oil<p><a href="https://mastodon.thenewoil.org/tags/NIST" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NIST</span></a> Finalizes Guidelines for Evaluating ‘<a href="https://mastodon.thenewoil.org/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a>’ Guarantees to De-Identify Data</p><p><a href="https://www.nist.gov/news-events/news/2025/03/nist-finalizes-guidelines-evaluating-differential-privacy-guarantees-de" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">nist.gov/news-events/news/2025</span><span class="invisible">/03/nist-finalizes-guidelines-evaluating-differential-privacy-guarantees-de</span></a></p><p><a href="https://mastodon.thenewoil.org/tags/privacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>privacy</span></a></p>
Aurélien Bellet<p>This article does a great job highlighting why DOGE is taking over the federal government so easily: federal systems centralize massive amounts of sensitive data, making them highly vulnerable to insider threats. The article concludes by pointing out that techniques like <a href="https://sigmoid.social/tags/FederatedLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FederatedLearning</span></a> and <a href="https://sigmoid.social/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> could help build more resilient systems 👏 <a href="https://sigmoid.social/tags/Privacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Privacy</span></a> <a href="https://sigmoid.social/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CyberSecurity</span></a></p><p><a href="https://www.nytimes.com/2025/02/21/opinion/musk-doge-personal-data.html?unlocked_article_code=1.yk4.ioNW.2SNQKCzmcCwR" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">nytimes.com/2025/02/21/opinion</span><span class="invisible">/musk-doge-personal-data.html?unlocked_article_code=1.yk4.ioNW.2SNQKCzmcCwR</span></a></p>
Simson Garfinkel<p>The OpenDP project has published a Q&amp;A with me on the occasion of the <a href="https://newsie.social/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> book, which is launching on March 25: <a href="https://opendp.org/blog/qa-simson-garfinkel-author-upcoming-book-differential-privacy" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">opendp.org/blog/qa-simson-garf</span><span class="invisible">inkel-author-upcoming-book-differential-privacy</span></a></p>
LavX News<p>Unlocking Algorithm Audits: Navigating Data Access in AI Transparency</p><p>As algorithms increasingly dictate critical decisions in society, the need for effective audits has never been more pressing. A new research article sheds light on the challenges of accessing data for...</p><p><a href="https://news.lavx.hu/article/unlocking-algorithm-audits-navigating-data-access-in-ai-transparency" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="ellipsis">news.lavx.hu/article/unlocking</span><span class="invisible">-algorithm-audits-navigating-data-access-in-ai-transparency</span></a></p><p><a href="https://mastodon.cloud/tags/news" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>news</span></a> <a href="https://mastodon.cloud/tags/tech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tech</span></a> <a href="https://mastodon.cloud/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> <a href="https://mastodon.cloud/tags/AlgorithmAudits" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AlgorithmAudits</span></a> <a href="https://mastodon.cloud/tags/DataTransparency" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataTransparency</span></a></p>
RoedigerRG<p><span class="h-card" translate="no"><a href="https://sigmoid.social/@aurelien_bellet" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>aurelien_bellet</span></a></span> </p><p><a href="https://social.anoxinon.de/tags/introduction" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>introduction</span></a> <a href="https://social.anoxinon.de/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://social.anoxinon.de/tags/TrustworthyAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TrustworthyAI</span></a> <a href="https://social.anoxinon.de/tags/decentralization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>decentralization</span></a> <a href="https://social.anoxinon.de/tags/privacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>privacy</span></a> <a href="https://social.anoxinon.de/tags/decentralized" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>decentralized</span></a> <a href="https://social.anoxinon.de/tags/FederatedLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FederatedLearning</span></a> <a href="https://social.anoxinon.de/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a> <a href="https://social.anoxinon.de/tags/data" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>data</span></a> <a href="https://social.anoxinon.de/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://social.anoxinon.de/tags/Fediverse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Fediverse</span></a> </p><p>I am really interested in these topics and I would like to hear every now and then some news or paper recommendation or sth like that.</p>
Aurélien Bellet<p>Time for a proper <a href="https://sigmoid.social/tags/introduction" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>introduction</span></a>! 👋 I'm a <a href="https://sigmoid.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> researcher at Inria, France, focusing on <a href="https://sigmoid.social/tags/TrustworthyAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TrustworthyAI</span></a>—especially <a href="https://sigmoid.social/tags/decentralization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>decentralization</span></a> &amp; <a href="https://sigmoid.social/tags/privacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>privacy</span></a>. I design algorithms that learn from <a href="https://sigmoid.social/tags/decentralized" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>decentralized</span></a> data (<a href="https://sigmoid.social/tags/FederatedLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FederatedLearning</span></a>) without memorizing personal data (<a href="https://sigmoid.social/tags/DifferentialPrivacy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DifferentialPrivacy</span></a>), working toward putting <a href="https://sigmoid.social/tags/data" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>data</span></a> &amp; <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> back in people's hands. Maybe one day, these ideas could be used in the <a href="https://sigmoid.social/tags/Fediverse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Fediverse</span></a>!</p>
ExploreLive feeds
About