ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
arXiv:1910.10994
Abstract
Zero-shot learning (ZSL) has received extensive attention recently especially in areas of fine-grained object recognition, retrieval, and image captioning. Due to the complete lack of training samples and high requirement of defense transferability, the ZSL model learned is particularly vulnerable against adversarial attacks. Recent work also showed adversarially robust generalization requires more data. This may significantly affect the robustness of ZSL. However, very few efforts have been devoted towards this direction. In this paper, we take an initial attempt, and propose a generic formulation to provide a systematical solution (named ATZSL) for learning a robust ZSL model. It is capable of achieving better generalization on various adversarial objects recognition while only losing a negligible performance on clean images for unseen classes, by casting ZSL into a min-max optimization problem. To address it, we design a defensive relation prediction network, which can bridge the seen and unseen class domains via attributes to generalize prediction and defense strategy. Additionally, our framework can be extended to deal with the poisoned scenario of unseen class attributes. An extensive group of experiments are then presented, demonstrating that ATZSL obtains remarkably more favorable trade-off between model transferability and robustness, over currently available alternatives under various settings.
14 pages, 9 figures, 10 tables, journal
References in corpus (6)
- Distilling the Knowledge in a Neural Network
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Zero-Shot Learning Through Cross-Modal Transfer
- Transductive Multi-view Zero-Shot Learning
- Hierarchical Prototype Learning for Zero-Shot Recognition
- Convolutional Prototype Learning for Zero-Shot Recognition