性能評価

Deep-CAPTCHA: a deep learning based CAPTCHA solver for vulnerability assessment

Authors: Zahra Noury, Mahdi Rezaei | Published: 2020-06-15 | Updated: 2020-06-24
性能評価
深層学習手法
脆弱性検出

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

Authors: Dingfan Chen, Tribhuvanesh Orekondy, Mario Fritz | Published: 2020-06-15 | Updated: 2021-03-15
アルゴリズム設計
性能評価
機械学習のプライバシー保護

Privacy-Preserving Technology to Help Millions of People: Federated Prediction Model for Stroke Prevention

Authors: Ce Ju, Ruihui Zhao, Jichao Sun, Xiguang Wei, Bo Zhao, Yang Liu, Hongshan Li, Tianjian Chen, Xinwei Zhang, Dashan Gao, Ben Tan, Han Yu, Chuning He, Yuan Jin | Published: 2020-06-15 | Updated: 2020-12-15
プライバシー設計原則
性能評価
機械学習のプライバシー保護

FMix: Enhancing Mixed Sample Data Augmentation

Authors: Ethan Harris, Antonia Marcu, Matthew Painter, Mahesan Niranjan, Adam Prügel-Bennett, Jonathon Hare | Published: 2020-02-27 | Updated: 2021-02-28
トレーニング手法
ロバスト性評価
性能評価

Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy

Authors: Aditya Saligrama, Guillaume Leclerc | Published: 2020-02-26
ロバスト性評価
性能評価
敵対的訓練

IoT Device Identification Using Deep Learning

Authors: Jaidip Kotak, Yuval Elovici | Published: 2020-02-25
データ管理システム
性能評価
機械学習手法

Neuron Shapley: Discovering the Responsible Neurons

Authors: Amirata Ghorbani, James Zou | Published: 2020-02-23 | Updated: 2020-11-13
性能評価
特徴重要度分析
脆弱性予測

Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks

Authors: Kirthi Shankar Sivamani, Rajeev Sahay, Aly El Gamal | Published: 2020-02-22
性能評価
敵対的訓練
防御手法

Using Single-Step Adversarial Training to Defend Iterative Adversarial Examples

Authors: Guanxiong Liu, Issa Khalil, Abdallah Khreishah | Published: 2020-02-22 | Updated: 2020-02-27
性能評価
敵対的サンプル
敵対的訓練

TensorShield: Tensor-based Defense Against Adversarial Attacks on Images

Authors: Negin Entezari, Evangelos E. Papalexakis | Published: 2020-02-18
性能評価
敵対的サンプル
防御手法