Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics
Authors: Jason W. Bentley, Daniel Gibney, Gary Hoppenworth, Sumit Kumar Jha | Published: 2020-09-11
敵対的攻撃手法
Second Order Optimization for Adversarial Robustness and Interpretability
Authors: Theodoros Tsiligkaridis, Jay Roberts | Published: 2020-09-10
Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
Authors: Ricardo Bigolin Lanfredi, Joyce D. Schroeder, Tolga Tasdizen | Published: 2020-09-10 | Updated: 2023-04-20
Adversarial Attack on Large Scale Graph
Authors: Jintang Li, Tao Xie, Liang Chen, Fenfang Xie, Xiangnan He, Zibin Zheng | Published: 2020-09-08 | Updated: 2021-05-06
Black Box to White Box: Discover Model Characteristics Based on Strategic Probing
Authors: Josh Kalin, Matthew Ciolino, David Noever, Gerry Dozier | Published: 2020-09-07
Dynamically Computing Adversarial Perturbations for Recurrent Neural Networks
Authors: Shankar A. Deka, Dušan M. Stipanović, Claire J. Tomlin | Published: 2020-09-07
Detection Defense Against Adversarial Attacks with Saliency Map
Authors: Dengpan Ye, Chuanxi Chen, Changrui Liu, Hao Wang, Shunzhi Jiang | Published: 2020-09-06
Vulnerability of Face Recognition Systems Against Composite Face Reconstruction Attack
Authors: Hadi Mansourifar, Weidong Shi | Published: 2020-08-23
Revisiting Adversarially Learned Injection Attacks Against Recommender Systems
Authors: Jiaxi Tang, Hongyi Wen, Ke Wang | Published: 2020-08-11 | Updated: 2020-08-28
Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification
Authors: Sina Däubener, Asja Fischer | Published: 2020-08-07 | Updated: 2020-08-17