TPAMI 2023 papers on Adversarial robustness and security
18 of the 664 papers published in TPAMI 2023 (2.7%) are on Adversarial robustness and security, compared with 3.3% at TPAMI 2022. They fall into 4 topics.
See TPAMI 2023 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 · 7 papers
- Influence-Driven Data Poisoning for Robust Recommender Systems (50 citations)
- Recognizing Object by Components With Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks (40 citations)
- Unified Adversarial Patch for Visible-Infrared Cross-Modal Attacks in the Physical World (37 citations)
- Comprehensive Vulnerability Evaluation of Face Recognition Systems to Template Inversion Attacks via 3D Face Reconstruction (34 citations)
- Jointly Defending DeepFake Manipulation and Adversarial Attack Using Decoy Mechanism (24 citations)
- 3D-Aware Adversarial Makeup Generation for Facial Privacy Protection (19 citations)
- Automatic Transformation Search Against Deep Leakage From Gradients (15 citations)
Certified and empirical robustness · 6 papers
- Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses (17 citations)
- An Introduction to Adversarially Robust Deep Learning (16 citations)
- GradMDM: Adversarial Attack on Dynamic Networks (11 citations)
- Variational Adversarial Defense: A Bayes Perspective for Adversarial Training (11 citations)
- LAFIT: Efficient and Reliable Evaluation of Adversarial Defenses With Latent Features (5 citations)
- Revisiting AUC-Oriented Adversarial Training With Loss-Agnostic Perturbations (4 citations)
