防御手法

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Authors: Kaidi Xu, Zhouxing Shi, Huan Zhang, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh | Published: 2020-02-28 | Updated: 2020-10-26
ロバスト性評価
脆弱性分析
防御手法

Certified Defense to Image Transformations via Randomized Smoothing

Authors: Marc Fischer, Maximilian Baader, Martin Vechev | Published: 2020-02-27 | Updated: 2021-08-25
ロバスト性評価
計算の整合性
防御手法

Entangled Watermarks as a Defense against Model Extraction

Authors: Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran, Nicolas Papernot | Published: 2020-02-27 | Updated: 2021-02-19
DNN IP保護手法
ロバスト性評価
防御手法

Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space

Authors: Camilo Pestana, Naveed Akhtar, Wei Liu, David Glance, Ajmal Mian | Published: 2020-02-25
ロバスト性評価
敵対的学習
防御手法

An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning

Authors: Xue Yang, Yan Feng, Weijun Fang, Jun Shao, Xiaohu Tang, Shu-Tao Xia, Rongxing Lu | Published: 2020-02-23 | Updated: 2021-08-15
プライバシー保護メカニズム
連合学習
防御手法

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

Robustness from Simple Classifiers

Authors: Sharon Qian, Dimitris Kalimeris, Gal Kaplun, Yaron Singer | Published: 2020-02-21
ロバスト性評価
敵対的訓練
防御手法

Adversarial Detection and Correction by Matching Prediction Distributions

Authors: Giovanni Vacanti, Arnaud Van Looveren | Published: 2020-02-21
アドバイス提供
敵対的訓練
防御手法

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

Authors: Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu | Published: 2020-02-21 | Updated: 2020-10-20
ロバスト性評価
最適化問題
防御手法

Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning

Authors: Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Yi Ouyang, I-Te Danny Hung, Chin-Hui Lee, Xiaoli Ma | Published: 2020-02-20
報酬メカニズム設計
脆弱性予測
防御手法