|
Workshop
|
|
Mathematical Theory of Adversarial Deep Learning
|
|
|
Workshop
|
|
Mathematical Theory of Adversarial Deep Learning
Xiao-Shan Gao · Lijia Yu · Shuang Liu
|
|
|
Poster
|
Thu 13:30
|
How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy
Raphaël Olivier · Bhiksha Raj
|
|
|
Poster
|
Thu 16:30
|
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
Yuzheng Hu · Fan Wu · Hongyang Zhang · Han Zhao
|
|
|
Workshop
|
|
CertViT: Certified Robustness of Pre-Trained Vision Transformers
|
|
|
Workshop
|
|
Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation
Wei-Ning Chen · Dan Song · Ayfer Ozgur · Peter Kairouz
|
|
|
Workshop
|
|
Near Optimal Adversarial Attack on UCB Bandits
|
|
|
Workshop
|
|
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
|
|
|
Workshop
|
|
CertViT: Certified Robustness of Pre-Trained Vision Transformers
Kavya Gupta · Sagar Verma
|
|
|
Workshop
|
|
Near Optimal Adversarial Attack on UCB Bandits
Shiliang Zuo
|
|
|
Workshop
|
|
Characterizing the Optimal 0−1 Loss for Multi-class Classification with a Test-time Attacker
|
|
|
Workshop
|
|
Shrink & Cert: Bi-level Optimization for Certified Robustness
|
|
