Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Authors: Dylan Slack, Sophie Hilgard, Emily Jia, Sameer Singh, Himabindu Lakkaraju | Published: 2019-11-06 | Updated: 2020-02-03
敵対的学習
Adversarial Example Detection by Classification for Deep Speech Recognition
Authors: Saeid Samizade, Zheng-Hua Tan, Chao Shen, Xiaohong Guan | Published: 2019-10-22
White-Box Adversarial Defense via Self-Supervised Data Estimation
Authors: Zudi Lin, Hanspeter Pfister, Ziming Zhang | Published: 2019-09-13
Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix
Authors: Chaomin Shen, Yaxin Peng, Guixu Zhang, Jinsong Fan | Published: 2019-09-13
Black-box Adversarial ML Attack on Modulation Classification
Authors: Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha | Published: 2019-08-01
Learning-Aided Physical Layer Attacks Against Multicarrier Communications in IoT
Authors: Alireza Nooraiepour, Waheed U. Bajwa, Narayan B. Mandayam | Published: 2019-08-01 | Updated: 2020-07-04
Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Authors: Utku Ozbulak, Arnout Van Messem, Wesley De Neve | Published: 2019-07-30
Adversarial Robustness Assessment: Why both $L_0$ and $L_\infty$ Attacks Are Necessary
Authors: Shashank Kotyan, Danilo Vasconcellos Vargas | Published: 2019-06-14 | Updated: 2020-07-16
Evolutionary Trigger Set Generation for DNN Black-Box Watermarking
Authors: Jia Guo, Miodrag Potkonjak | Published: 2019-06-11 | Updated: 2021-02-14
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Authors: Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin | Published: 2019-06-10 | Updated: 2019-10-14