On the relationship between class selectivity, dimensionality, and robustness
Authors: Matthew L. Leavitt, Ari S. Morcos | Published: 2020-07-08 | Updated: 2020-10-13
Poisoning
Backdoor attacks and defenses in feature-partitioned collaborative learning
Authors: Yang Liu, Zhihao Yi, Tianjian Chen | Published: 2020-07-07
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Authors: Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard A. Moser, Gerhard Widmer | Published: 2020-07-06
Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
Authors: Samuel Henrique Silva, Peyman Najafirad | Published: 2020-07-01 | Updated: 2020-07-03
Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detection
Authors: Deqiang Li, Qianmu Li | Published: 2020-06-30
Model-Targeted Poisoning Attacks with Provable Convergence
Authors: Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, Yuan Tian | Published: 2020-06-30 | Updated: 2021-04-21
Orthogonal Deep Models As Defense Against Black-Box Attacks
Authors: Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian | Published: 2020-06-26
Deep Partition Aggregation: Provable Defense against General Poisoning Attacks
Authors: Alexander Levine, Soheil Feizi | Published: 2020-06-26 | Updated: 2021-03-18
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
Authors: Kaizhao Liang, Jacky Y. Zhang, Boxin Wang, Zhuolin Yang, Oluwasanmi Koyejo, Bo Li | Published: 2020-06-25 | Updated: 2021-07-08
Subpopulation Data Poisoning Attacks
Authors: Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger, Alina Oprea | Published: 2020-06-24 | Updated: 2021-05-12