NeurIPS 2018 accepted papers on Adversarial robustness and security
33 of the 1,008 papers accepted at NeurIPS 2018 (3.3%) are on Adversarial robustness and security, compared with 0.7% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 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 · 24 papers
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (982 citations)
- Adversarially Robust Generalization Requires More Data (500 citations)
- Fast and Effective Robustness Certification (243 citations)
- Scaling provable adversarial defenses (222 citations)
- Semidefinite relaxations for certifying robustness to adversarial examples (189 citations)
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (178 citations)
- Efficient Formal Safety Analysis of Neural Networks (173 citations)
- Adversarial vulnerability for any classifier (154 citations)
- Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks (154 citations)
- Constructing Unrestricted Adversarial Examples with Generative Models (123 citations)
- Invariant Representations without Adversarial Training (101 citations)
- Hessian-based Analysis of Large Batch Training and Robustness to Adversaries (95 citations)
and 12 more in the interactive map.
Attacks on text and graphs · 7 papers
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks (245 citations)
- Adversarial Examples that Fool both Computer Vision and Time-Limited Humans (155 citations)
- Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples (52 citations)
- Contamination Attacks and Mitigation in Multi-Party Machine Learning (36 citations)
- Online Robust Policy Learning in the Presence of Unknown Adversaries (23 citations)
- Unorganized Malicious Attacks Detection (13 citations)
- Non-Adversarial Mapping with VAEs (9 citations)
Black-box and transfer attacks · 1 paper
Backdoor and poisoning · 1 paper
- Spectral Signatures in Backdoor Attacks (367 citations)
