This research offers a significant advancement in privacy-enhancing instance encoding, providing stronger theoretical guarantees and broader applicability. It's a must-read for those interested in data privacy and encoding techniques.
A new study introduces a family of tighter bounds for privacy-enhancing instance encoding, applicable to deterministic encoders and extending beyond MSE to other norm-based metrics. The bounds are evaluated across various encoders, datasets, and attacks, showing improved performance over existing methods.
Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before sharing, with the hope that the encoding process retains utility but makes it hard to reconstruct the original data. However, most work offers no theoretical guarantee that the encoding process is actually irreversible. A recent work derived a mean-squared error (MSE) bound limiting any adversary's reconstruction accuracy, offering one of the first theoretical results in this domain. This bound, however, has three critical limitations: it is often too loose, only works with randomized encoders (excluding many deterministic encoders practitioners use), and only bounds MSE. We introduce a family of new bounds that (1) are tighter, (2) applicable even to fully deterministic encoders, and (3) can extend beyond MSE to other norm-based similarity metrics, by properly accounting for the encoder's spectral structure. We evaluate our bounds across a range of encoders, datasets, and attacks, showing they hold consistently and improve upon the existing bound.