AAAI 2019 accepted papers on Adversarial robustness and security
21 of the 1,147 papers accepted at AAAI 2019 (1.8%) are on Adversarial robustness and security, compared with 1.1% at AAAI 2018. They fall into 3 topics.
See AAAI 2019 in the interactive map
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
Attacks on text and graphs · 11 papers
- Perceptual-Sensitive GAN for Generating Adversarial Patches (296 citations)
- One-Class Adversarial Nets for Fraud Detection (178 citations)
- Sparse Adversarial Perturbations for Videos (151 citations)
- Adversarial Learning for Weakly-Supervised Social Network Alignment (91 citations)
- Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks (77 citations)
- Resisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders (74 citations)
- On Structured Argumentation with Conditional Preferences (20 citations)
- Find Me if You Can: Deep Software Clone Detection by Exploiting the Contest between the Plagiarist and the Detector (7 citations)
- Deception in Finitely Repeated Security Games
- Improving Hypernymy Prediction via Taxonomy Enhanced Adversarial Learning
- Re-Evaluating ADEM: A Deeper Look at Scoring Dialogue Responses
Certified and empirical robustness · 9 papers
- Interpretation of Neural Networks Is Fragile (890 citations)
- The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure (107 citations)
- Sensitivity Analysis of Deep Neural Networks (82 citations)
- Connecting the Digital and Physical World: Improving the Robustness of Adversarial Attacks (80 citations)
- RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications (57 citations)
- Verifying Robustness of Gradient Boosted Models (49 citations)
- The Adversarial Attack and Detection under the Fisher Information Metric (42 citations)
- Towards Reliable Learning for High Stakes Applications (13 citations)
- Distributionally Adversarial Attack
