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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “eavesdropper”

Dual MINE-based Neural Secure Communications under Gaussian Wiretap Channelcs.IT

Proposes a secure communication method independent of eavesdropper's decoder.

problem Lack of practical security constraints in existing methods.

method Dual MINE-based neural secure communications model.

result Security performance is not affected by eavesdropper's decoding means.

secure communications neural networks Gaussian wiretap channel MINE eavesdropper

2021-02-25abs ↗pdf ↗

How to Make 5G Communications "Invisible": Adversarial Machine Learning for Wireless Privacyeess.SP

Adversarial machine learning hides 5G communications from eavesdroppers.

problem Hiding 5G communications from eavesdroppers using DL classifiers.

method Craft adversarial perturbations to fool DL classifiers.

result Adversarial perturbations can hide 5G communications with high probability.

5G wireless privacy adversarial machine learning covert communications deep learning

2020-05-15abs ↗pdf ↗

Covert Communications via Adversarial Machine Learning and Reconfigurable Intelligent Surfaceseess.SP

Adversarial perturbations and RIS interaction vectors improve covert communication.

problem Covert communication in the presence of RISs.

method Designing RIS interaction vectors to balance receiver and eavesdropper detection, adding adversarial perturbations to signals.

result Adversarial perturbations and RIS interaction vectors can be jointly designed to boost covert communications.

covert communication reconfigurable intelligent surfaces adversarial machine learning deep neural networks signal detection

2021-12-21abs ↗pdf ↗

Privacy-Aware Communication Over a Wiretap Channel with Generative Networkscs.IT

A privacy-preserving method for transmitting data over a wiretap channel using generative networks.

problem Privacy protection in communication over a wiretap channel.

method Data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC).

result The approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute.

privacy wiretap channel generative networks joint source channel coding end-to-end learning

2021-10-08abs ↗pdf ↗

Ensuring superior learning outcomes and data security for authorized learnerstat.ML

Theorem ensures superior learning outcomes for authorized learners with quantum label encoding.

problem Ensuring data security for authorized learners in machine learning.

method Quantum label encoding and PAC learning framework.

result Authorized learners achieve superior learning outcomes while eavesdroppers do not.

quantum label encoding PAC learning machine learning data security authorized learner

2025-01-01abs ↗pdf ↗

Privacy Aware Offloading of Deep Neural Networkscs.LG

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but introduces a privacy risk since the operator of the cloud is not necessarily trustworthy.…

2018-05-30abs ↗pdf ↗

On Model Protection in Federated Learning against Eavesdropping Attackscs.CR

Study protects federated learning models from eavesdropping attacks.

problem Protecting client models in federated learning from eavesdropping adversaries.

method Theoretical analysis and numerical experiments examining various factors.

result Theoretical and experimental results show the effectiveness of protection methods.

federated learning eavesdropping attacks model protection theoretical analysis numerical experiments

2025-04-02abs ↗pdf ↗

Private Networked Federated Learning for Nonsmooth Objectivesmath.OC

Paper develops privacy-preserving federated learning for nonsmooth objectives.

problem Solving nonsmooth objective functions in a privacy-preserving manner.

method Zero-concentrated differential privacy (zCDP) with Gaussian noise, distributed ADMM, and approximation of augmented Lagrangian.

result The algorithm achieves a competitive privacy-accuracy trade-off and converges to the exact solution.

federated learning nonsmooth optimization zero-concentrated differential privacy ADMM Gaussian noise

2023-06-24abs ↗pdf ↗

The Privacy Power of Correlated Noise in Decentralized Learningcs.LG

Decor protects decentralized learning models from curious users.

problem Privacy violation in decentralized learning.

method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.

result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.

decentralized learning differential privacy correlated noise SGD privacy protection

2024-05-02abs ↗pdf ↗

Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcs.LG

A-FADMM improves FL scalability and privacy via wireless channel perturbations and interference.

problem Challenges in model training due to wireless channel randomness and interference.

method Formulated a novel constrained optimization problem and proposed A-FADMM framework.

result Proves convergence and privacy guarantees for A-FADMM under time-varying channels.

Federated Learning Wireless Channels Privacy Bandwidth Efficiency Scalability

2020-07-03abs ↗pdf ↗

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescs.LG

This paper improves privacy in federated learning without a trusted server.

problem Privacy in federated learning with silos that distrust each other.

method Introduces Inter-Silo Record-Level Differential Privacy (ISRL-DP) and accelerated algorithms for convex and smooth losses.

result Achieves optimal privacy and accuracy tradeoffs in federated learning.

federated learning differential privacy private machine learning cross-silo learning convex optimization

2021-06-17abs ↗pdf ↗