Closed gonzalo-munillag closed 1 year ago
Floating-point Vulnerability Protection.
Prevent exploiting vulnerabilities that could lead to privacy leakage.
There is no documentation that states the use of floating-point vulnerability protection as in https://scholar.google.com/citations?view_op=view_citation&hl=en&user=hg3A9TgAAAAJ&citation_for_view=hg3A9TgAAAAJ:dhFuZR0502QC and https://research.ibm.com/publications/secure-random-sampling-in-differential-privacy
Additional code should be added to cover such vulnerability.
Sample from discrete distributions.
Other libraries like IBM's diffpriblib accounts for this, and they also enable ML.
Hi @gonzalo-munillag
Thank you for your question and interest in Opacus.
If I am not mistaken, this vulnerability is fixed and documented in here which uses the fix in here.
I am going to close this task for now, but if you feel like your issue wasn't handled, feel free to comment here and reopen!
🚀 Feature
Floating-point Vulnerability Protection.
Motivation
Prevent exploiting vulnerabilities that could lead to privacy leakage.
There is no documentation that states the use of floating-point vulnerability protection as in https://scholar.google.com/citations?view_op=view_citation&hl=en&user=hg3A9TgAAAAJ&citation_for_view=hg3A9TgAAAAJ:dhFuZR0502QC and https://research.ibm.com/publications/secure-random-sampling-in-differential-privacy
Pitch
Additional code should be added to cover such vulnerability.
Alternatives
Sample from discrete distributions.
Additional context
Other libraries like IBM's diffpriblib accounts for this, and they also enable ML.