La Privacy e Cybersec per le aziende
Osservatorio a cura del dott. V. Spataro 

Milano, sab 2 dicembre 2023:, Social media non vi temo - Ascolti tra Marketing e AI

   dizionario 2023-08-08 ·  NEW:   Appunta · Stampa · pdf

Katharina Koerner on LinkedIn: Home | 17 comments


Documento annotato il 08.08.2023 Fonte:


L'analisi è riservata agli iscritti. Segui la newsletter dell'Osservatorio oppure il Podcast iscrizione gratuita 30 giorni




estimated reading time: 2 min

View profile for Katharina Koerner

Katharina Koerner

AI Governance, Privacy, privacy Tech, Responsible AI, Open Source, Security • Law, Policy, Research, Speaker, Community • privacy compliance of emerging tech • Bridging the world between privacy, policy, and IT

Differential privacy (DP) is increasingly referred to as the state-of-the-art data anonymization technique. I often hear that the market demand for differential privacy skills exceeds the skills available. Here is a great opportunity to engage in a open source differential privacy project, led and advised by global leaders in this promising approach for enhanced privacy and data protection. Differential privacy is a rigorous mathematical definition of privacy for statistical analysis and ML. In a nutshell, an algorithm is said to be differentially private if by looking at the output, one cannot tell whether any individual's data was included in the original dataset or not. At last month's "Eyes Off-Data Summit", organized by Oblivious and Antigranular, I had the honor to meet Salil Vadhan, Professor of Computer Science and Applied Mathematics, Harvard University, who - together with Gary King, University Professor, Director, IQSS, Harvard University - is Faculty Director of OpenDP. OpenDP is a community effort to build a trustworthy suite of open-source tools for generating differentially private statistical releases. The target use cases for OpenDP are to enable government, industry, and academic institutions to safely and confidently share sensitive data to support scientifically oriented research and exploration in the public interest. The OpenDP Library is a modular collection of statistical algorithms that adhere to the definition of differential privacy. It can be used to build applications of privacy-preserving computations, using a number of different models of privacy. OpenDP is implemented in Rust, with bindings for easy use from Python. The architecture of the OpenDP Library is based on a conceptual framework for expressing privacy-aware computations. This framework is described in the paper A Programming Framework for OpenDP by Marco Gaboardi, Michael Hay and Salil Vadhan: Apart from engaging in various ways which you can find here:, a great next opportunity to learn more about DP is coming up. Organized the same week as the Theory and Practice of Differential privacy workshop (TPDP) in Boston (see:, the OpenDP team is looking forward to hosting the first IN-PERSON OpenDP Community meeting on Friday, September 29th (with opportunities to join virtually). A detailed agenda and location information will soon be available, but you can already REGISTER here:



See more comments

Explore topics


Testo del 2023-08-08 Fonte:


i commenti sono anonimi e inviati via mail e cancellati dopo aver migliorato la voce alla quale si riferiscono: non sono archiviati; comunque non lasciare dati particolari. Si applica la privacy policy.

Ricevi gli aggiornamenti su Katharina Koerner on LinkedIn: Home | 17 comments e gli altri post del sito:

Email: (gratis Info privacy)

Nota: il dizionario è aggiornato frequentemente con correzioni e giurisprudenza