#DifferentialPrivacy starter pack by @thegautamkamath.bsky.social
Differential Privacy Researchers
Join the conversation
go.bsky.app
November 19, 2024 at 7:30 PM
#DifferentialPrivacy starter pack by @thegautamkamath.bsky.social
I Built Analytics That Cannot See You
paragraph.com/@metaend/ana...
#DifferentialPrivacy #PrivacyByDesign #OpenSource #Astro #PrivacyEngineering #WebDevelopment
paragraph.com/@metaend/ana...
#DifferentialPrivacy #PrivacyByDesign #OpenSource #Astro #PrivacyEngineering #WebDevelopment
I Built Analytics That Cannot See You
Every analytics tool makes you a promise. I built one where the promise is unnecessary, because the math makes individual visits unknowable.
paragraph.com
June 8, 2026 at 10:42 AM
I Built Analytics That Cannot See You
paragraph.com/@metaend/ana...
#DifferentialPrivacy #PrivacyByDesign #OpenSource #Astro #PrivacyEngineering #WebDevelopment
paragraph.com/@metaend/ana...
#DifferentialPrivacy #PrivacyByDesign #OpenSource #Astro #PrivacyEngineering #WebDevelopment
New blog post by @stein.ke on #DifferentialPrivacy: what happens when you modify the definition of neighbors to make it asymmetric? Why would you do that, and does that buy you anything?
differentialprivacy.org/one-sided/
differentialprivacy.org/one-sided/
One-Sided Differential Privacy
Differential privacy is defined in terms of pairs of neighboring datasets. That is, \(M\) is \((\varepsilon,\delta)\)-differentially private if, for all measurable events \(T\) and all neighboring pai...
differentialprivacy.org
May 15, 2026 at 8:28 PM
New blog post by @stein.ke on #DifferentialPrivacy: what happens when you modify the definition of neighbors to make it asymmetric? Why would you do that, and does that buy you anything?
differentialprivacy.org/one-sided/
differentialprivacy.org/one-sided/
🔏𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘆 𝗧𝘂𝗲𝘀𝗱𝗮𝘆!📖
#DifferentialPrivacy is an increasingly popular, though controversial, approach. This week, @benrothke.bsky.social provides a Hall of Fame recommendation of @simson.net 's 𝘋𝘪𝘧𝘧𝘦𝘳𝘦𝘯𝘵𝘪𝘢𝘭 𝘗𝘳𝘪𝘷𝘢𝘤𝘺, from @mitpress.bsky.social.
👉 tinyurl.com/2s3jk4cn
#CybersecurityBooks #DP
#DifferentialPrivacy is an increasingly popular, though controversial, approach. This week, @benrothke.bsky.social provides a Hall of Fame recommendation of @simson.net 's 𝘋𝘪𝘧𝘧𝘦𝘳𝘦𝘯𝘵𝘪𝘢𝘭 𝘗𝘳𝘪𝘷𝘢𝘤𝘺, from @mitpress.bsky.social.
👉 tinyurl.com/2s3jk4cn
#CybersecurityBooks #DP
October 14, 2025 at 1:35 PM
🔏𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘆 𝗧𝘂𝗲𝘀𝗱𝗮𝘆!📖
#DifferentialPrivacy is an increasingly popular, though controversial, approach. This week, @benrothke.bsky.social provides a Hall of Fame recommendation of @simson.net 's 𝘋𝘪𝘧𝘧𝘦𝘳𝘦𝘯𝘵𝘪𝘢𝘭 𝘗𝘳𝘪𝘷𝘢𝘤𝘺, from @mitpress.bsky.social.
👉 tinyurl.com/2s3jk4cn
#CybersecurityBooks #DP
#DifferentialPrivacy is an increasingly popular, though controversial, approach. This week, @benrothke.bsky.social provides a Hall of Fame recommendation of @simson.net 's 𝘋𝘪𝘧𝘧𝘦𝘳𝘦𝘯𝘵𝘪𝘢𝘭 𝘗𝘳𝘪𝘷𝘢𝘤𝘺, from @mitpress.bsky.social.
👉 tinyurl.com/2s3jk4cn
#CybersecurityBooks #DP
Here's my latest blog alert on sublinear #algorithms and #differentialprivacy in a wide-ranging conversation with @ccanonne.github.io!
scieye.wordpress.com/2025/09/17/e...
#randomness #BigData #SciComm @simonsinstitute.bsky.social @sydney.edu.au
scieye.wordpress.com/2025/09/17/e...
#randomness #BigData #SciComm @simonsinstitute.bsky.social @sydney.edu.au
Exploring algorithms and privacy in big data with clément canonne
In this age of identity theft and privacy invasion, could you order a bowl of chips online, without giving away your mother’s maiden name? Gathered in a local pub in Sydney, computer scientist Clém…
scieye.wordpress.com
September 18, 2025 at 12:58 PM
Here's my latest blog alert on sublinear #algorithms and #differentialprivacy in a wide-ranging conversation with @ccanonne.github.io!
scieye.wordpress.com/2025/09/17/e...
#randomness #BigData #SciComm @simonsinstitute.bsky.social @sydney.edu.au
scieye.wordpress.com/2025/09/17/e...
#randomness #BigData #SciComm @simonsinstitute.bsky.social @sydney.edu.au
I'm talking about #differentialPrivacy on the SecureTalk podcast by @StrikeGraph.
Website: www.securetalkpodcast.com
Youtube: youtu.be/eZFgxKsFvYg?...
Apple Podcast: podcasts.apple.com/us/podcast/p...
Spotify: open.spotify.com/episode/4o9h...
SoundCloud: soundcloud.com/user-7796943...
Website: www.securetalkpodcast.com
Youtube: youtu.be/eZFgxKsFvYg?...
Apple Podcast: podcasts.apple.com/us/podcast/p...
Spotify: open.spotify.com/episode/4o9h...
SoundCloud: soundcloud.com/user-7796943...
March 26, 2025 at 5:23 PM
I'm talking about #differentialPrivacy on the SecureTalk podcast by @StrikeGraph.
Website: www.securetalkpodcast.com
Youtube: youtu.be/eZFgxKsFvYg?...
Apple Podcast: podcasts.apple.com/us/podcast/p...
Spotify: open.spotify.com/episode/4o9h...
SoundCloud: soundcloud.com/user-7796943...
Website: www.securetalkpodcast.com
Youtube: youtu.be/eZFgxKsFvYg?...
Apple Podcast: podcasts.apple.com/us/podcast/p...
Spotify: open.spotify.com/episode/4o9h...
SoundCloud: soundcloud.com/user-7796943...
ELSA Board member @ahonkela.bsky.social contributed to the paper"Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning",presented at @neuripsconf.bsky.social'25
Article ➡️ www.helsinki.fi/en/faculty-s...
#MachineLearning #DifferentialPrivacy #PrivacyGuarantees
Article ➡️ www.helsinki.fi/en/faculty-s...
#MachineLearning #DifferentialPrivacy #PrivacyGuarantees
How to ensure anonymity of AI systems? | Faculty of Science | University of Helsinki
When training artificial intelligence systems, developers need to use privacy-enhancing technologies to ensure that the subjects of the training data are not exposed, new study suggests.
www.helsinki.fi
December 10, 2025 at 9:18 AM
ELSA Board member @ahonkela.bsky.social contributed to the paper"Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning",presented at @neuripsconf.bsky.social'25
Article ➡️ www.helsinki.fi/en/faculty-s...
#MachineLearning #DifferentialPrivacy #PrivacyGuarantees
Article ➡️ www.helsinki.fi/en/faculty-s...
#MachineLearning #DifferentialPrivacy #PrivacyGuarantees
Do you work with detailed population data from the 2020 Census?
A brand new brief from the U.S. Census Bureau and PRB helps you understand the data structure and disclosure avoidance:
www.census.gov/library/publ...
#2020Census #DisclosureAvoidance #DifferentialPrivacy #Data #Statistics
A brand new brief from the U.S. Census Bureau and PRB helps you understand the data structure and disclosure avoidance:
www.census.gov/library/publ...
#2020Census #DisclosureAvoidance #DifferentialPrivacy #Data #Statistics
Disclosure Avoidance and the 2020 Census: How the TopDown Algorithm Works
This brief describes how differential privacy works and how it is applied to the 2020 Census Detailed DHC-A.
www.census.gov
November 3, 2023 at 6:24 PM
Do you work with detailed population data from the 2020 Census?
A brand new brief from the U.S. Census Bureau and PRB helps you understand the data structure and disclosure avoidance:
www.census.gov/library/publ...
#2020Census #DisclosureAvoidance #DifferentialPrivacy #Data #Statistics
A brand new brief from the U.S. Census Bureau and PRB helps you understand the data structure and disclosure avoidance:
www.census.gov/library/publ...
#2020Census #DisclosureAvoidance #DifferentialPrivacy #Data #Statistics
In my thesis,
‘Designing Secure and Knowledge-Aware Recommender Systems Leveraging Data Properties and Graph Structures,’
I explored #RecSys 💡, enhancing #Graph-based models 🕸️ with knowledge graphs and safeguarding data using #DifferentialPrivacy 🔒
‘Designing Secure and Knowledge-Aware Recommender Systems Leveraging Data Properties and Graph Structures,’
I explored #RecSys 💡, enhancing #Graph-based models 🕸️ with knowledge graphs and safeguarding data using #DifferentialPrivacy 🔒
January 26, 2025 at 11:13 AM
In my thesis,
‘Designing Secure and Knowledge-Aware Recommender Systems Leveraging Data Properties and Graph Structures,’
I explored #RecSys 💡, enhancing #Graph-based models 🕸️ with knowledge graphs and safeguarding data using #DifferentialPrivacy 🔒
‘Designing Secure and Knowledge-Aware Recommender Systems Leveraging Data Properties and Graph Structures,’
I explored #RecSys 💡, enhancing #Graph-based models 🕸️ with knowledge graphs and safeguarding data using #DifferentialPrivacy 🔒
🎥 Free Privacy-Preserving ML Workshop!
Learn how to protect privacy in AI systems
2 Sessions: Dec 4 (This Wed!) & Dec 18, covering:
- #FederatedLearning
- #DifferentialPrivacy
- #HomomorphicEncryption
Register → bit.ly/3Ziz6qN
Learn how to protect privacy in AI systems
2 Sessions: Dec 4 (This Wed!) & Dec 18, covering:
- #FederatedLearning
- #DifferentialPrivacy
- #HomomorphicEncryption
Register → bit.ly/3Ziz6qN
December 2, 2024 at 9:39 PM
🎥 Free Privacy-Preserving ML Workshop!
Learn how to protect privacy in AI systems
2 Sessions: Dec 4 (This Wed!) & Dec 18, covering:
- #FederatedLearning
- #DifferentialPrivacy
- #HomomorphicEncryption
Register → bit.ly/3Ziz6qN
Learn how to protect privacy in AI systems
2 Sessions: Dec 4 (This Wed!) & Dec 18, covering:
- #FederatedLearning
- #DifferentialPrivacy
- #HomomorphicEncryption
Register → bit.ly/3Ziz6qN
Launching the session was Bao & Bindschaedler's "R+R: Towards Reliable and Generalizable Differentially Private Machine Learning," which scrutinizes 11 DPML techniques for #reproducibility. (www.acsac.org/2024/p...) 2/6
#DifferentialPrivacy #ML #MachineLearning
#DifferentialPrivacy #ML #MachineLearning
September 11, 2025 at 2:01 PM
Launching the session was Bao & Bindschaedler's "R+R: Towards Reliable and Generalizable Differentially Private Machine Learning," which scrutinizes 11 DPML techniques for #reproducibility. (www.acsac.org/2024/p...) 2/6
#DifferentialPrivacy #ML #MachineLearning
#DifferentialPrivacy #ML #MachineLearning
Is privacy in the digital age possible?
Cynthia Dwork from Harvard University addressed this topic at the ISTA Lecture earlier this week. Her talk on #DifferentialPrivacy demonstrated how it safeguards personal data in industry and government.
Thanks to everyone who attended this event.
Cynthia Dwork from Harvard University addressed this topic at the ISTA Lecture earlier this week. Her talk on #DifferentialPrivacy demonstrated how it safeguards personal data in industry and government.
Thanks to everyone who attended this event.
December 12, 2025 at 9:42 AM
Is privacy in the digital age possible?
Cynthia Dwork from Harvard University addressed this topic at the ISTA Lecture earlier this week. Her talk on #DifferentialPrivacy demonstrated how it safeguards personal data in industry and government.
Thanks to everyone who attended this event.
Cynthia Dwork from Harvard University addressed this topic at the ISTA Lecture earlier this week. Her talk on #DifferentialPrivacy demonstrated how it safeguards personal data in industry and government.
Thanks to everyone who attended this event.
#DifferentialPrivacy made the top position of @techreview's "Recent books from the MIT community" in the March/April edition.
www.technologyreview.com/2025/02/25/1...
www.technologyreview.com/2025/02/25/1...
Recent books from the MIT community
March/April 2025
www.technologyreview.com
March 29, 2025 at 9:05 PM
#DifferentialPrivacy made the top position of @techreview's "Recent books from the MIT community" in the March/April edition.
www.technologyreview.com/2025/02/25/1...
www.technologyreview.com/2025/02/25/1...
#DifferentialPrivacy has a cover.
Paperback
ISBN: 9780262551656
Pub date: March 25, 2025
Publisher: The MIT Press
244 pp., 5 x 7 in, 22 b&w illus.
mitpress.mit.edu/978026255165...
Paperback
ISBN: 9780262551656
Pub date: March 25, 2025
Publisher: The MIT Press
244 pp., 5 x 7 in, 22 b&w illus.
mitpress.mit.edu/978026255165...
November 14, 2024 at 1:37 AM
#DifferentialPrivacy has a cover.
Paperback
ISBN: 9780262551656
Pub date: March 25, 2025
Publisher: The MIT Press
244 pp., 5 x 7 in, 22 b&w illus.
mitpress.mit.edu/978026255165...
Paperback
ISBN: 9780262551656
Pub date: March 25, 2025
Publisher: The MIT Press
244 pp., 5 x 7 in, 22 b&w illus.
mitpress.mit.edu/978026255165...
Im zweiten Teil des DOAG.tv-Interviews mit dem Sicherheitsexperten @ABuckenhofer geht es um #Datenmaskierungstechniken wie #DifferentialPrivacy sowie um #BigData als potentielle Gefahr für den #Datenschutz. http://ow.ly/g2bH50AM7GB #DOAG2019 #doagtv #datanalytics
December 1, 2024 at 7:33 AM
Im zweiten Teil des DOAG.tv-Interviews mit dem Sicherheitsexperten @ABuckenhofer geht es um #Datenmaskierungstechniken wie #DifferentialPrivacy sowie um #BigData als potentielle Gefahr für den #Datenschutz. http://ow.ly/g2bH50AM7GB #DOAG2019 #doagtv #datanalytics
The Great Screenshot Scandal: Microsoft Recall and Signal’s DRM Shield
dailysecurityreview.com/podcasts/the...
#ML #federatedlearning #differentialprivacy #edgeAI #QML #GDPR #privacy
Federated Learning www.geeksforgeeks.org/machine-lear...
Differential Privacy aimultiple.com/differential...
dailysecurityreview.com/podcasts/the...
#ML #federatedlearning #differentialprivacy #edgeAI #QML #GDPR #privacy
Federated Learning www.geeksforgeeks.org/machine-lear...
Differential Privacy aimultiple.com/differential...
The Great Screenshot Scandal: Microsoft Recall and Signal’s DRM Shield - Podcasts
In this episode, we dive deep into the growing tension between AI innovation and data privacy through the lens of a major controversy: Microsoft’s Windows 11
dailysecurityreview.com
October 5, 2025 at 8:17 PM
The Great Screenshot Scandal: Microsoft Recall and Signal’s DRM Shield
dailysecurityreview.com/podcasts/the...
#ML #federatedlearning #differentialprivacy #edgeAI #QML #GDPR #privacy
Federated Learning www.geeksforgeeks.org/machine-lear...
Differential Privacy aimultiple.com/differential...
dailysecurityreview.com/podcasts/the...
#ML #federatedlearning #differentialprivacy #edgeAI #QML #GDPR #privacy
Federated Learning www.geeksforgeeks.org/machine-lear...
Differential Privacy aimultiple.com/differential...
Differential Privacy 101 in human words:
1️⃣ Take a batch of sequences
2️⃣ Clip each gradient so no single example can dominate
3️⃣ Add calibrated Gaussian noise 💉
4️⃣ Update weights
5️⃣ Repeat across a trillion tokens
#AI #Privacy #MachineLearning #DeepLearning #DifferentialPrivacy
1️⃣ Take a batch of sequences
2️⃣ Clip each gradient so no single example can dominate
3️⃣ Add calibrated Gaussian noise 💉
4️⃣ Update weights
5️⃣ Repeat across a trillion tokens
#AI #Privacy #MachineLearning #DeepLearning #DifferentialPrivacy
November 28, 2025 at 4:00 AM
Differential Privacy 101 in human words:
1️⃣ Take a batch of sequences
2️⃣ Clip each gradient so no single example can dominate
3️⃣ Add calibrated Gaussian noise 💉
4️⃣ Update weights
5️⃣ Repeat across a trillion tokens
#AI #Privacy #MachineLearning #DeepLearning #DifferentialPrivacy
1️⃣ Take a batch of sequences
2️⃣ Clip each gradient so no single example can dominate
3️⃣ Add calibrated Gaussian noise 💉
4️⃣ Update weights
5️⃣ Repeat across a trillion tokens
#AI #Privacy #MachineLearning #DeepLearning #DifferentialPrivacy
Our main point is that #DifferentialPrivacy is pretty great because it allows informed discussions of privacy guarantees, but configuring them is not just a technical choice, it’s a major policy decision with direct implications for user trust, fairness, and transparency.
August 28, 2025 at 12:15 PM
Our main point is that #DifferentialPrivacy is pretty great because it allows informed discussions of privacy guarantees, but configuring them is not just a technical choice, it’s a major policy decision with direct implications for user trust, fairness, and transparency.
OpenDP is happy to announce the release of DP Wizard, an interactive tool exploring the effect of different parameter choices, and an assistant for implementing them with the OpenDP library. #differentialprivacy
https://opendp.org/blog/dp-wizard-easy-way-get-started-differential-privacy-and-opendp
https://opendp.org/blog/dp-wizard-easy-way-get-started-differential-privacy-and-opendp
December 19, 2024 at 6:29 PM
OpenDP is happy to announce the release of DP Wizard, an interactive tool exploring the effect of different parameter choices, and an assistant for implementing them with the OpenDP library. #differentialprivacy
https://opendp.org/blog/dp-wizard-easy-way-get-started-differential-privacy-and-opendp
https://opendp.org/blog/dp-wizard-easy-way-get-started-differential-privacy-and-opendp
U.S. Census Bureau Bans Noise Infusion from Statistical Products
#differentialprivacy #statisticaldata #privacy
https://singulism.com/en/2026-06-14-census-bureau-noise-infusion-ban
#differentialprivacy #statisticaldata #privacy
https://singulism.com/en/2026-06-14-census-bureau-noise-infusion-ban
U.S. Census Bureau Bans Noise Infusion from Statistical Products
The U.S. Department of Commerce has completely banned noise infusion (a core method of differential privacy) in statistical products from the Census Bureau and the Bureau of Economic Analysis. This ar
singulism.com
June 14, 2026 at 9:13 PM
U.S. Census Bureau Bans Noise Infusion from Statistical Products
#differentialprivacy #statisticaldata #privacy
https://singulism.com/en/2026-06-14-census-bureau-noise-infusion-ban
#differentialprivacy #statisticaldata #privacy
https://singulism.com/en/2026-06-14-census-bureau-noise-infusion-ban
Differential Privacy is revolutionizing data security in the AI era! By adding noise to queries, it protects sensitive info while maintaining utility. A game-changer for healthcare, finance & more! 🌐🤖 #DataPrivacy #AI #CyberSecurity #DifferentialPrivacy snip.ly/qa5sxq
The Role of Differential Privacy in Protecting Sensitive Information in the Era of Artificial Intelligence
Differential privacy protects data by adding noise to queries addressing Artificial Intelligence -era privacy challenges.
snip.ly
March 7, 2025 at 3:34 PM
Differential Privacy is revolutionizing data security in the AI era! By adding noise to queries, it protects sensitive info while maintaining utility. A game-changer for healthcare, finance & more! 🌐🤖 #DataPrivacy #AI #CyberSecurity #DifferentialPrivacy snip.ly/qa5sxq
Republicans want to ban differential privacy in the Census, citing data distortion. But removing it could expose personal info, risking privacy for millions. It’s a battle over how we protect data in the age of AI.
www.wired.com/story/...
#DataPrivacy #Census #Policy #Ethics #DifferentialPrivacy
www.wired.com/story/...
#DataPrivacy #Census #Policy #Ethics #DifferentialPrivacy
The Republican Plan to Reform the Census Could Put Everyone’s Privacy at Risk
A little-known algorithmic process called “differential privacy” helps keep census data anonymous. Conservatives want it gone.
www.wired.com
October 29, 2025 at 3:49 PM
Republicans want to ban differential privacy in the Census, citing data distortion. But removing it could expose personal info, risking privacy for millions. It’s a battle over how we protect data in the age of AI.
www.wired.com/story/...
#DataPrivacy #Census #Policy #Ethics #DifferentialPrivacy
www.wired.com/story/...
#DataPrivacy #Census #Policy #Ethics #DifferentialPrivacy
My own personal main takeaway from this years Eyes Off Data Summit was the conversation around the evolution of data access, privacy and security and how to think about the Zero Trust principles around the future of data. www.linkedin.com/pulse/7th-ge... #ai #ml #differentialprivacy #pets
7th Generation Data Security: Zero Trust Data Access & Entitlements
The Evolution of Data Security: Why Zero Trust Is the Future Over the years, data security has seen multiple transformations, each defined by the evolving threat landscape and advancements in technolo...
www.linkedin.com
December 1, 2024 at 11:25 AM
My own personal main takeaway from this years Eyes Off Data Summit was the conversation around the evolution of data access, privacy and security and how to think about the Zero Trust principles around the future of data. www.linkedin.com/pulse/7th-ge... #ai #ml #differentialprivacy #pets