ポイズニング

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method

Authors: Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin | Published: 2019-07-26 | Updated: 2019-12-04
ポイズニング
効果的な摂動手法
敵対的移転性

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

Authors: Yuxin Ma, Tiankai Xie, Jundong Li, Ross Maciejewski | Published: 2019-07-17 | Updated: 2019-10-03
バックドア攻撃
ポイズニング
敵対的攻撃手法

Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methods

Authors: Arif Siddiqi | Published: 2019-07-17
ポイズニング
敵対的サンプル
敵対的攻撃手法

Helen: Maliciously Secure Coopetitive Learning for Linear Models

Authors: Wenting Zheng, Raluca Ada Popa, Joseph E. Gonzalez, Ion Stoica | Published: 2019-07-16 | Updated: 2019-09-03
MPCアルゴリズム
ポイズニング
暗号化技術

Stateful Detection of Black-Box Adversarial Attacks

Authors: Steven Chen, Nicholas Carlini, David Wagner | Published: 2019-07-12
ポイズニング
攻撃検出
敵対的攻撃

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

Authors: Francesco Croce, Matthias Hein | Published: 2019-07-03 | Updated: 2020-07-20
ポイズニング
敵対的サンプルの脆弱性
敵対的攻撃

Comment on “Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network”

Authors: Roland S. Zimmermann | Published: 2019-07-01
ポイズニング
敵対的攻撃
深層学習手法

Improving Black-box Adversarial Attacks with a Transfer-based Prior

Authors: Shuyu Cheng, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu | Published: 2019-06-17 | Updated: 2020-07-26
ポイズニング
敵対的摂動手法
最適化問題

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Authors: Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang, Huan Zhang, Ilya Razenshteyn, Sebastien Bubeck | Published: 2019-06-09 | Updated: 2020-01-10
ポイズニング
敵対的学習
防御手法

Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness

Authors: Walt Woods, Jack Chen, Christof Teuscher | Published: 2019-06-07 | Updated: 2019-08-06
ポイズニング
敵対的サンプル
敵対的訓練