#differentialprivacy — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #differentialprivacy, aggregated by home.social.
-
"The consequences will be dire for utility or for privacy, and possibly both. It's hard to understate this point: future statistical releases will either be useless compared to past ones, or they will be incredibly unsafe.
For starters, taking away useful tools from the disclosure avoidance toolbox will always lead to more painful privacy/utility trade-offs. The whole point of this research field is to better understand and quantify privacy risk, and develop better tools to mitigate this risk while preserving utility.
For statistical releases, differential privacy is simply the best tool we have right now. It provides a finer way of quantifying trade-offs, and allows us to get more utility out of the data than competing techniques at similar privacy levels. If you take it away, you're left with techniques that either have worse utility at similar levels of privacy, or worse privacy for the same utility.
But all competing techniques also rely on noise addition. The Cell Key method, used at other statistical agencies, adds noise to statistics. Swapping, used from 1990 to 2010 for the U.S. Census, also injects randomness into the process. Sampling is everywhere in statistical work2. Hell, even imputation technically adds noise to the data3!
By contrast, coarsening and suppression are very blunt instruments. They only work in situations where the statistics are already very coarse, and not too many of them are published.
(...)
It makes sense: privacy attacks on statistical releases are about solving a system of equations. It is such an easier task when you know for sure that the statistics are all perfectly accurate. Noise forces you to compute probabilities, quantify the uncertainty, carefully consider baselines, and so on. That's why randomness is such a useful tool for disclosure avoidance! Even without formal guarantees, it makes attakcs a lot harder. Take it away and attacks become trivial."
https://desfontain.es/blog/banning-noise.html
#USA #Census #Statistics #DifferentialPrivacy -
"The consequences will be dire for utility or for privacy, and possibly both. It's hard to understate this point: future statistical releases will either be useless compared to past ones, or they will be incredibly unsafe.
For starters, taking away useful tools from the disclosure avoidance toolbox will always lead to more painful privacy/utility trade-offs. The whole point of this research field is to better understand and quantify privacy risk, and develop better tools to mitigate this risk while preserving utility.
For statistical releases, differential privacy is simply the best tool we have right now. It provides a finer way of quantifying trade-offs, and allows us to get more utility out of the data than competing techniques at similar privacy levels. If you take it away, you're left with techniques that either have worse utility at similar levels of privacy, or worse privacy for the same utility.
But all competing techniques also rely on noise addition. The Cell Key method, used at other statistical agencies, adds noise to statistics. Swapping, used from 1990 to 2010 for the U.S. Census, also injects randomness into the process. Sampling is everywhere in statistical work2. Hell, even imputation technically adds noise to the data3!
By contrast, coarsening and suppression are very blunt instruments. They only work in situations where the statistics are already very coarse, and not too many of them are published.
(...)
It makes sense: privacy attacks on statistical releases are about solving a system of equations. It is such an easier task when you know for sure that the statistics are all perfectly accurate. Noise forces you to compute probabilities, quantify the uncertainty, carefully consider baselines, and so on. That's why randomness is such a useful tool for disclosure avoidance! Even without formal guarantees, it makes attakcs a lot harder. Take it away and attacks become trivial."
https://desfontain.es/blog/banning-noise.html
#USA #Census #Statistics #DifferentialPrivacy -
Hype for the Future 103F: Differential Privacy Defined
Introduction While personally identifiable information is often expected to remain private, and the most sensitive of information, such as passwords, shall be kept even more private to just the self, differential privacy is also a concept that may be appropriate for demonstrative purposes with online resources. To become a public figure, and to become an ethically-sourced public figure in particular, at least a basic understanding of the concept of differential privacy shall be identified. […]https://novatopflex.wordpress.com/2026/02/11/hype-for-the-future-103f-differential-privacy-defined/
-
Hype for the Future 103F: Differential Privacy Defined
Introduction While personally identifiable information is often expected to remain private, and the most sensitive of information, such as passwords, shall be kept even more private to just the self, differential privacy is also a concept that may be appropriate for demonstrative purposes with online resources. To become a public figure, and to become an ethically-sourced public figure in particular, at least a basic understanding of the concept of differential privacy shall be identified. […]https://novatopflex.wordpress.com/2026/02/11/hype-for-the-future-103f-differential-privacy-defined/
-
Hype for the Future 103F: Differential Privacy Defined
Introduction While personally identifiable information is often expected to remain private, and the most sensitive of information, such as passwords, shall be kept even more private to just the self, differential privacy is also a concept that may be appropriate for demonstrative purposes with online resources. To become a public figure, and to become an ethically-sourced public figure in particular, at least a basic understanding of the concept of differential privacy shall be identified. […]https://novatopflex.wordpress.com/2026/02/11/hype-for-the-future-103f-differential-privacy-defined/
-
Apple überarbeitet Siri: „LLM Siri“ soll Neuanfang bringen
Apple steht vor einem grundlegenden Umbau seines Sprachassistenten Siri. Ziel ist eine neue, KI-basierte Version namens „LLM Siri“. Diese Entwicklung folgt auf Problem
https://www.apfeltalk.de/magazin/news/apple-ueberarbeitet-siri-llm-siri-soll-neuanfang-bringen/
#KI #News #AppleAIStrategie #AppleIntelligence #AppleSprachassistent #DifferentialPrivacy #GenerativeKI #JohnGiannandrea #KIApple #LLMSiri #PerplexityAI #SiriUpdate -
Apple überarbeitet Siri: „LLM Siri“ soll Neuanfang bringen
Apple steht vor einem grundlegenden Umbau seines Sprachassistenten Siri. Ziel ist eine neue, KI-basierte Version namens „LLM Siri“. Diese Entwicklung folgt auf Problem
https://www.apfeltalk.de/magazin/news/apple-ueberarbeitet-siri-llm-siri-soll-neuanfang-bringen/
#KI #News #AppleAIStrategie #AppleIntelligence #AppleSprachassistent #DifferentialPrivacy #GenerativeKI #JohnGiannandrea #KIApple #LLMSiri #PerplexityAI #SiriUpdate -
Firefox under fire for enabling ‘privacy-protecting ad measurements’
https://stackdiary.com/firefox-under-fire-for-enabling-privacy-protecting-ad-measurements/
#Firefox #Privacy #Advertising #Mozilla #Controversy #Tracking #UserConcerns #DataProtection #WebStandards #AdMeasurement #DefaultSettings #Backlash #PrivacyPreserving #Attribution #API #UserConsent #Aggregation #DifferentialPrivacy #Encryption #Anonymous #OptOut #MarketShare #UserDecline #AdTech #DataCollection #BrowserWars #TechEthics #UserRights #InternetFreedom #DigitalPrivacy
-
Firefox under fire for enabling ‘privacy-protecting ad measurements’
https://stackdiary.com/firefox-under-fire-for-enabling-privacy-protecting-ad-measurements/
#Firefox #Privacy #Advertising #Mozilla #Controversy #Tracking #UserConcerns #DataProtection #WebStandards #AdMeasurement #DefaultSettings #Backlash #PrivacyPreserving #Attribution #API #UserConsent #Aggregation #DifferentialPrivacy #Encryption #Anonymous #OptOut #MarketShare #UserDecline #AdTech #DataCollection #BrowserWars #TechEthics #UserRights #InternetFreedom #DigitalPrivacy
-
@je5perl @ilumium And how will we know whether #ISRG passes a list of website visits to the NSA? https://www.isrg.org/privacy-policy/ isn't reassuring.
Claims of #DifferentialPrivacy would be more credible if enforced at the individual browser level. Presumably this would require at least that the browser send reports at intervals of several days, aggregating information from individual websites/publishers and adding noise about non-existing ads. But how to prevent collusion on deanonymising these? #AdTech
-
@je5perl @ilumium And how will we know whether #ISRG passes a list of website visits to the NSA? https://www.isrg.org/privacy-policy/ isn't reassuring.
Claims of #DifferentialPrivacy would be more credible if enforced at the individual browser level. Presumably this would require at least that the browser send reports at intervals of several days, aggregating information from individual websites/publishers and adding noise about non-existing ads. But how to prevent collusion on deanonymising these? #AdTech
-
#Heise: "Richter zweifelt an zentraler #Massenspeicherung von #Gesundheitsdaten" "Das Sozialgericht Berlin verhandelte über eine Klage gegen den Transfer sensibler Gesundheitsdaten an ein Forschungszentrum und #DifferentialPrivacy -Ansätze.": https://www.heise.de/news/Richter-zweifelt-an-zentraler-Massenspeicherung-von-Gesundheitsdaten-7312977.html