It is found that task capability and privacy leakage are fundamentally coupled: more capable models are systematically leakier, with no model in the evaluation able to decouple the two.
Soumya Sharma, Ayana Hussain, H. H. Arcolezi et al.· 0 citations
The results suggest that private dense retrieval is already practical for moderately sized, privacy-sensitive corpora when minute-scale latency is acceptable, and formulates a two-round cryptographic protocol that provides both guarantees.
Louis Tremblay Thibault, Sofiane Azogagh, Marc-Olivier Killijian et al.· arXiv.org· 0 citations
This work introduces SCALPEL, a contrastive sparse autoencoder designed to learn more selective forget features and shows theoretically that contrastive training promotes target-selective features and that the selection score controls expected background knowledge perturbation.
The experiments show that the learned tree topology provides strong interpretability by consistently isolating minority subgroups, which provides a transparent mapping between the model architecture and the data's latent group structure, while yielding competitive robustness with state-of-the-art methods.
Ankur Garg, Ulrich Aivodji, S. Kahou et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.