|
Workshop
|
|
When Can Linear Learners be Robust to Indiscriminate Poisoning Attacks?
|
|
|
Workshop
|
|
Sharpness-Aware Minimization Alone can Improve Adversarial Robustness
Zeming Wei · Jingyu Zhu · Yihao Zhang
|
|
|
Workshop
|
|
A Theoretical Perspective on the Robustness of Feature Extractors
|
|
|
Workshop
|
|
Scoring Black-Box Models for Adversarial Robustness
|
|
|
Workshop
|
|
R-LPIPS: An Adversarially Robust Perceptual Similarity Metric
|
|
|
Workshop
|
|
Characterizing the Optimal 0−1 Loss for Multi-class Classification with a Test-time Attacker
|
|
|
Workshop
|
|
Certified Calibration: Bounding Worst-Case Calibration under Adversarial Attacks
|
|
|
Workshop
|
|
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
|
|
|
Workshop
|
|
Like Oil and Water: Group Robustness and Poisoning Defenses Don’t Mix
|
|
|
Poster
|
Thu 16:30
|
Adversarial robustness of amortized Bayesian inference
Manuel Gloeckler · Michael Deistler · Jakob Macke
|
|
|
Affinity Workshop
|
Mon 19:15
|
Is ReLU Adversarially Robust?
Korn Sooksatra · Greg Hamerly · Pablo Rivas
|
|
|
Poster
|
Thu 16:30
|
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Yuzheng Hu · Fan Wu · Hongyang Zhang · Han Zhao
|
|
