NeurIPS 2019 accepted papers on Adversarial robustness and security
52 of the 1,429 papers accepted at NeurIPS 2019 (3.6%) are on Adversarial robustness and security, compared with 3.3% at NeurIPS 2018. They fall into 4 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Certified and empirical robustness · 39 papers
- Adversarial Examples Are Not Bugs, They Are Features (389 citations)
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (261 citations)
- Adversarial Robustness through Local Linearization (190 citations)
- Certified Adversarial Robustness with Additive Noise (185 citations)
- Are Labels Required for Improving Adversarial Robustness? (174 citations)
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (133 citations)
- Adversarial Training and Robustness for Multiple Perturbations (124 citations)
- Fooling Neural Network Interpretations via Adversarial Model Manipulation (117 citations)
- A Little Is Enough: Circumventing Defenses For Distributed Learning (98 citations)
- Image Synthesis with a Single (Robust) Classifier (89 citations)
- Functional Adversarial Attacks (86 citations)
- A Fourier Perspective on Model Robustness in Computer Vision (84 citations)
and 27 more in the interactive map.
Attacks on text and graphs · 9 papers
- Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training (118 citations)
- Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks (67 citations)
- A New Defense Against Adversarial Images: Turning a Weakness into a Strength (66 citations)
- Quantum Wasserstein Generative Adversarial Networks (55 citations)
- Certifiable Robustness to Graph Perturbations (52 citations)
- Adversarial Self-Defense for Cycle-Consistent GANs (31 citations)
- Adversarial Music: Real world Audio Adversary against Wake-word Detection System (23 citations)
- Cross-Modal Learning with Adversarial Samples (19 citations)
- Learning from brains how to regularize machines (11 citations)
