Face Recognition
Face recognition research aims to develop accurate and robust systems for identifying individuals from their facial images. Current efforts focus on improving performance under challenging conditions (e.g., low-resolution images, occlusions), mitigating biases stemming from demographic imbalances in training data, and enhancing the explainability and security of these systems through techniques like knowledge distillation and adversarial watermarking. These advancements have significant implications for various applications, including security, law enforcement, and healthcare, while also raising important ethical considerations regarding privacy and fairness.
Papers
Powerful Physical Adversarial Examples Against Practical Face Recognition Systems
Inderjeet Singh, Toshinori Araki, Kazuya Kakizaki
On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations
Philipp Terhörst, Florian Bierbaum, Marco Huber, Naser Damer, Florian Kirchbuchner, Kiran Raja, Arjan Kuijper
Evaluating Proposed Fairness Models for Face Recognition Algorithms
John J. Howard, Eli J. Laird, Yevgeniy B. Sirotin, Rebecca E. Rubin, Jerry L. Tipton, Arun R. Vemury
Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition
Xiao Yang, Yinpeng Dong, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu