analiza aiqbench
This research advances the theoretical guarantees of instance encoding, a critical technique for protecting data privacy when sharing information with untrusted servers. By deriving tighter bounds that apply to both randomized and deterministic encoders, the study addresses significant gaps in existing literature regarding reconstruction accuracy. These improvements ensure more robust privacy preservation across diverse encoder architectures and attack scenarios.
Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding
arXiv:2608.23382v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Cryptography and Security (cs.CR)
arXiv:2608.23382 [cs.LG]
(or arXiv:2608.23382v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.23382 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 267 cuvinte
Subiecte conexe
Scene-Q: Confidence-Aware Coarse-to-Fine Querying of 3D Scenes with Selective VLM Reasoning
arXiv · 18 sept. 2026
ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation
arXiv · 6 oct. 2026
On the Expressive Power and Capacity of Quantum Data Reuploaders
arXiv · 8 oct. 2026
Federated Self-Supervised Modulation Classification under Non-IID and Imbalanced Data
arXiv · 19 aug. 2026