diff options
| author | Jan Aalmoes <jan.aalmoes@inria.fr> | 2024-09-11 00:10:50 +0200 |
|---|---|---|
| committer | Jan Aalmoes <jan.aalmoes@inria.fr> | 2024-09-11 00:10:50 +0200 |
| commit | bf5b05a84e877391fddd1b0a0b752f71ec05e901 (patch) | |
| tree | 149609eeff1d475cd60f398f0e4bfd786c5d281c /synthetic/conclusion.tex | |
| parent | 03556b31409ac5e8b81283d3a6481691c11846d7 (diff) | |
Preuve existe f pas cca equivalant exists f BA pas randomguess
Diffstat (limited to 'synthetic/conclusion.tex')
| -rw-r--r-- | synthetic/conclusion.tex | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/synthetic/conclusion.tex b/synthetic/conclusion.tex new file mode 100644 index 0000000..bb6dd17 --- /dev/null +++ b/synthetic/conclusion.tex @@ -0,0 +1,6 @@ +Even though synthetic dataset are promising regarding users' data protection, in itself it does not bring guaranties regarding attribute inference attack. +For future work we suggest that applying fairness regularization during the training of the generator could be a way to remove bias toward sensitive attributes. + +Concerning membership inference attack, synthetic data reduce the overall risk while still leaving an attack surface on some outliers points. +Differential privacy is a way to reduce the risk on outliers but removing entirely the risk while keeping some level of utility is impossible. +Hence more work in this direction is required.
\ No newline at end of file |