AIセキュリティポータルbot

Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Authors: Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy, Biplav Srivastava | Published: 2018-11-09
バックドア攻撃対策
バックドア攻撃用の毒データの検知
ポイズニング攻撃

YODA: Enabling computationally intensive contracts on blockchains with Byzantine and Selfish nodes

Authors: Sourav Das, Vinay Joseph Ribeiro, Abhijeet Anand | Published: 2018-11-08 | Updated: 2018-12-18
ビザンチン攻撃対策
合意形成アルゴリズム
悪意のあるノード検出

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning

Authors: Florian Tramèr, Pascal Dupré, Gili Rusak, Giancarlo Pellegrino, Dan Boneh | Published: 2018-11-08 | Updated: 2019-08-26
ポイズニング
悪意のあるコンテンツ生成
敵対的学習

MixTrain: Scalable Training of Verifiably Robust Neural Networks

Authors: Shiqi Wang, Yizheng Chen, Ahmed Abdou, Suman Jana | Published: 2018-11-06 | Updated: 2018-12-01
モデル性能評価
ロバスト性向上
敵対的学習

Exploring Connections Between Active Learning and Model Extraction

Authors: Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, Songbai Yan | Published: 2018-11-05 | Updated: 2019-11-20
オンライン学習
モデル性能評価
モデル抽出攻撃

Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls

Authors: Yi Shi, Yalin E. Sagduyu, Kemal Davaslioglu, Jason H. Li | Published: 2018-11-05
オンライン学習
メンバーシップ推論
敵対的サンプル

Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference

Authors: Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Muhammad Shafique | Published: 2018-11-05
IoTセキュリティ
ポイズニング攻撃
モデル抽出攻撃

FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning

Authors: Faiq Khalid, Muhammmad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique | Published: 2018-11-04
モデル抽出攻撃
攻撃の評価
防御手法

SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

Authors: Hassan Ali, Faiq Khalid, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique | Published: 2018-11-04 | Updated: 2020-05-15
トリガーの検知
ロバスト性向上
攻撃の評価

QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

Authors: Faiq Khalid, Hassan Ali, Hammad Tariq, Muhammad Abdullah Hanif, Semeen Rehman, Rehan Ahmed, Muhammad Shafique | Published: 2018-11-04 | Updated: 2020-05-14
モデルの頑健性保証
量子化手法
防御手法