TPAMI 2022 papers on Adversarial robustness and security
19 of the 583 papers published in TPAMI 2022 (3.3%) are on Adversarial robustness and security, compared with 1.9% at TPAMI 2021. They fall into 4 topics.
See TPAMI 2022 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
Certified and empirical robustness · 11 papers
- Solving Inverse Problems With Deep Neural Networks – Robustness Included? (165 citations)
- GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization (65 citations)
- On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective (46 citations)
- Adversarial Robustness Via Fisher-Rao Regularization (37 citations)
- Adversarially Robust One-class Novelty Detection (30 citations)
- Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators (23 citations)
- Towards Robust Person Re-Identification by Defending Against Universal Attackers (23 citations)
- Stylized Adversarial Defense (21 citations)
- Shaping Deep Feature Space Towards Gaussian Mixture for Visual Classification (17 citations)
- Defensive Few-shot Learning (14 citations)
- On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error (12 citations)
Black-box and transfer attacks · 5 papers
- Adversarial Sticker: A Stealthy Attack Method in the Physical World (156 citations)
- Query-Efficient Black-Box Adversarial Attack With Customized Iteration and Sampling (75 citations)
- Simultaneously Optimizing Perturbations and Positions for Black-Box Adversarial Patch Attacks (71 citations)
- Adversarial Examples Generation for Deep Product Quantization Networks on Image Retrieval (36 citations)
- An Intermediate-level Attack Framework on The Basis of Linear Regression (10 citations)
