adversarial-1

Neural Network Security

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in neural-network-security-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find neural-network-security-3 models and implementations

Datasets

SafeEdit

Subtasks

Website Fingerprinting Defense

Most implemented papers

Hacking Neural Networks: A Short Introduction

Michael D Kissner•Sun Nov 17 2019

How deep learning in security works is given and the basic methods of exploitation are explored, but also the offensive capabilities deep learning enabled tools provide are looked at.

2

Content

0

Paper Graph

Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis

Yuwei Sun, H. Ochiai, Jun Sakuma•Mon Mar 21 2022

The Attacking Distance-aware Attack (ADA) is proposed to enhance a poisoning attack by finding the optimized target class in the feature space by deducing pair-wise distances between different classes in the latent feature space from shared model parameters based on the backward error analysis.

20 0

Paper Graph

Adding a benchmark result helps the community track progress.