On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “InstaHide”

InstaHide's Sample Complexity When Mixing Two Private Imagescs.LG

Paper analyzes InstaHide's security, recovering all private images with provable guarantee.

problem Protecting privacy of training data in neural networks.

method Unified framework to understand and analyze attacks on InstaHide, presenting a new algorithm to recover all private images with provable guarantee.

result InstaHide is computationally secure but not information-theoretically secure when mixing two private images.

InstaHide privacy protection private images sample complexity neural networks

2020-11-24abs ↗pdf ↗

On InstaHide, Phase Retrieval, and Sparse Matrix Factorizationcs.LG

Study on InstaHide's security, linking to phase retrieval problem.

problem Security of InstaHide scheme for private dataset sharing.

method Design of a provable algorithm for private vector recovery.

result Private vectors can be recovered using synthetic vectors and public vectors.

InstaHide Phase Retrieval Sparse Matrix Factorization Security Distributed Learning

2020-11-23abs ↗pdf ↗

InstaHide: Instance-hiding Schemes for Private Distributed Learningcs.CR

InstaHide encrypts images for privacy in distributed learning.

problem Private training of deep neural networks on distributed data.

method Encryption of training images with one-time secret keys and pixel-wise masks.

result Preserves privacy with minor accuracy loss, secure against known attacks.

private deep learning distributed training image encryption privacy-preserving one-time secret key

2020-10-06abs ↗pdf ↗